[HN Gopher] macOS 26.2 enables fast AI clusters with RDMA over T...
       ___________________________________________________________________
        
       macOS 26.2 enables fast AI clusters with RDMA over Thunderbolt
        
       Author : guiand
       Score  : 512 points
       Date   : 2025-12-12 20:41 UTC (1 days ago)
        
 (HTM) web link (developer.apple.com)
 (TXT) w3m dump (developer.apple.com)
        
       | nodesocket wrote:
       | Can we get proper HDR support first in macOS? If I enable HDR on
       | my LG OLED monitor it looks completely washed out and blacks are
       | grey. Windows 11 HDR works fine.
        
         | Razengan wrote:
         | Really? I thought it's always been that HDR was notorious on
         | Windows, hopeless on Linux, and only really worked in a plug-
         | and-play manner on Mac, unless your display has an incorrect
         | profile or something/
         | 
         | https://www.youtube.com/shorts/sx9TUNv80RE
        
           | heavyset_go wrote:
           | Works well on Linux, just toggle a checkmark in the settings.
        
           | masspro wrote:
           | MacOS does wash out SDR content in HDR mode specifically on
           | non-Apple monitors. An HDR video playing in windowed mode
           | will look fine but all the UI around it has black and white
           | levels very close to grey.
           | 
           | Edit: to be clear, macOS itself (Cocoa elements) is all SDR
           | content and thus washed out.
        
             | Starmina wrote:
             | That's intended behavior for monitor limited in peak
             | brightness
        
               | nodesocket wrote:
               | I don't think so. Windows 11 has a HDR calibration
               | utility that allows you to adjust brightness and HDR and
               | it maintains blacks being perfectly black (especially
               | with my OLED). When I enable HDR on macOS whatever
               | settings I try, including adjusting brightness and
               | contrast on the monitor the blacks look completely washed
               | out and grey. HDR DOES seem to work correctly on macOS
               | but only if you use Mac displays.
        
               | masspro wrote:
               | That's the statement I found last time I went down this
               | rabbit hole, that they don't have physical brightness
               | info for third-party displays so it just can't be done
               | any better. But I don't understand how this can lead to
               | making the black point terrible. Black should be the one
               | color every emissive colorspace agrees on.
        
               | kmeisthax wrote:
               | Actually, intended behavior in general. Even on their own
               | displays the UI looks grey when HDR is playing.
               | 
               | Which, personally, I find to be extremely ugly and gross
               | and I do not understand why they thought this was a good
               | idea.
        
             | adastra22 wrote:
             | Huh, so that's why HDR looks like shit on my Mac Studio.
        
             | crazygringo wrote:
             | Define "washed out"?
             | 
             | The white and black levels of the UX are supposed to stay
             | in SDR. That's a feature not a bug.
             | 
             | If you mean the interface isn't bright enough, that's
             | intended behavior.
             | 
             | If the black point is somehow raised, then that's bizarre
             | and definitely unintended behavior. And I honestly can't
             | even imagine what could be causing that to happen. It does
             | seem like that it would have to be a serious macOS bug.
             | 
             | You should post a photo of your monitor, comparing a black
             | #000 image in Preview with a pitch-black frame from a
             | video. People edit HDR video on Macs, and I've never heard
             | of this happening before.
        
             | robflynn wrote:
             | Oh, that explains why it looked so odd when I enabled HDR
             | on my Studio.
        
         | m-ack-toddler wrote:
         | AI is arguably more important than whatever gaming gimmick
         | you're talking about.
        
       | simonw wrote:
       | I follow the MLX team on Twitter and they sometimes post about
       | using MLX on two or more joined together Macs to run models that
       | need more than 512GB of RAM.
       | 
       | A couple of examples:
       | 
       | Kimi K2 Thinking (1 trillion parameters):
       | https://x.com/awnihannun/status/1986601104130646266
       | 
       | DeepSeek R1 (671B):
       | https://x.com/awnihannun/status/1881915166922863045 - that one
       | came with setup instructions in a Gist:
       | https://gist.github.com/awni/ec071fd27940698edd14a4191855bba...
        
         | awnihannun wrote:
         | For a bit more context, those posts are using pipeline
         | parallelism. For N machines put the first L/N layers on machine
         | 1, next L/N layers on machine 2, etc. With pipeline parallelism
         | you don't get a speedup over one machine - it just buys you the
         | ability to use larger models than you can fit on a single
         | machine.
         | 
         | The release in Tahoe 26.2 will enable us to do fast tensor
         | parallelism in MLX. Each layer of the model is sharded across
         | all machines. With this type of parallelism you can get close
         | to N-times faster for N machines. The main challenge is latency
         | since you have to do much more frequent communication.
        
           | liuliu wrote:
           | But that's only for prefilling right? Or is it beneficial for
           | decoding too (I guess you can do KV lookup on shards, not
           | sure how much speed-up that will be though).
        
             | zackangelo wrote:
             | No you use tensor parallelism in both cases.
             | 
             | The way it typically works in an attention block is:
             | smaller portions of the Q, K and V linear layers are
             | assigned to each node and are processed independently.
             | Attention, rope norm etc is run on the node-specific output
             | of that. Then, when the output linear layer is applied an
             | "all reduce" is computed which combines the output of all
             | the nodes.
             | 
             | EDIT: just realized it wasn't clear -- this means that each
             | node ends up holding a portion of the KV cache specific to
             | its KV tensor shards. This can change based on the specific
             | style of attention (e.g., in GQA where there are fewer KV
             | heads than ranks you end up having to do some replication
             | etc)
        
               | liuliu wrote:
               | I usually call it "head parallelism" (which is a type of
               | tensor parallelism, but paralllelize for small clusters,
               | and specific to attention). That is what you described:
               | sharding input tensor by number of heads and send to
               | respective Q, K, V shard. They can do Q / K / V
               | projection, rope, qk norm whatever and attention all
               | inside that particular shard. The out projection will be
               | done in that shard too but then need to all reduce sum
               | amongst shard to get the final out projection broadcasted
               | to every participating shard, then carry on to do
               | whatever else themselves.
               | 
               | I am asking, however, is whether that will speed up
               | decoding as linearly as it would for prefilling.
        
               | awnihannun wrote:
               | Right, my comment was mostly about decoding speed. For
               | prefill you can get a speed up but there you are less
               | latency bound.
               | 
               | In our benchmarks with MLX / mlx-lm it's as much as 3.5x
               | for token generation (decoding) at batch size 1 over 4
               | machines. In that case you are memory bandwidth bound so
               | sharding the model and KV cache 4-ways means each machine
               | only needs to access 1/4th as much memory.
        
               | liuliu wrote:
               | Oh! That's great to hear. Congrats! Now, I want to get
               | the all-to-all primitives ready in s4nnc...
        
             | monster_truck wrote:
             | Even if it wasn't outright beneficial for decoding by
             | itself, it would still allow you to connect a second
             | machine running a smaller, more heavily quantized version
             | of the model for speculative decoding which can net you >4x
             | without quality loss
        
           | dpe82 wrote:
           | > The main challenge is latency since you have to do much
           | more frequent communication.
           | 
           | Earlier this year I experimented with building a cluster to
           | do tensor parallelism across large cache CPUs (AMD EPYC 7773X
           | have 768mb of L3). My thought was to keep an entire model in
           | SRAM and take advantage of the crazy memory bandwidth between
           | CPU cores and their cache, and use Infiniband between nodes
           | for the scatter/gather operations.
           | 
           | Turns out the sum of intra-core latency and PCIe latency
           | absolutely dominate. The Infiniband fabric is damn fast once
           | you get data to it, but getting it there quickly is a
           | struggle. CXL would help but I didn't have the budget for
           | newer hardware. Perhaps modern Apple hardware is better for
           | this than x86 stuff.
        
             | wmf wrote:
             | That's how Groq works. A cluster of LPUv2s would probably
             | be faster and cheaper than an Infiniband cluster of Epycs.
        
               | fooblaster wrote:
               | what is an lpuv2
        
               | wmf wrote:
               | The chip that Groq makes.
        
               | dpe82 wrote:
               | Yeah I'm familiar; I was hoping I could do something
               | related on previous generation commodity(ish) hardware.
               | It didn't work but I learned a ton.
        
           | aimanbenbaha wrote:
           | Exo-Labs is an open source project that allows this too,
           | pipeline parallelism I mean not the latter, and it's device
           | agnostic meaning you can daisy-chain anything you have that
           | has memory and the implementation will intelligently shard
           | model layers across them, though its slow but scales linearly
           | with concurrent requests.
           | 
           | Exo-Labs: https://github.com/exo-explore/exo
        
         | andy99 wrote:
         | I'm hoping this isn't as attractive as it sounds for non-
         | hobbyists because the performance won't scale well to parallel
         | workloads or even context processing, where parallelism can be
         | better used.
         | 
         | Hopefully this makes it really nice for people that want the
         | experiment with LLMs and have a local model but means well
         | funded companies won't have any reason to grab them all vs
         | GPUs.
        
           | codazoda wrote:
           | I haven't looked yet but I might be a candidate for something
           | like this, maybe. I'm RAM constrained and, to a lesser
           | extent, CPU constrained. It would be nice to offload some of
           | that. That said, I don't think I would buy a cluster of Macs
           | for that. I'd probably buy a machine that can take a GPU.
        
             | ChrisMarshallNY wrote:
             | I'm not particularly interested in training models, but it
             | would be nice to have eGPUs again. When Apple Silicon came
             | out, support for them dried up. I sold my old BlackMagic
             | eGPU.
             | 
             | That said, the need for them also faded. The new chips have
             | performance every bit as good as the eGPU-enhanced Intel
             | chips.
        
               | andy_ppp wrote:
               | eGPU with an Apple accelerator with a bunch or RAM and
               | GPU cores could be really interesting honestly. I'm
               | pretty sure they are capable of designing something very
               | competitive especially in terms of performance per watt.
        
           | bigyabai wrote:
           | The lack of official Linux/BSD support is enough to make it
           | DOA for any serious large-scale deployment. Until Apple
           | figures out what they're doing on that front, you've got
           | nothing to worry about.
        
             | Eggpants wrote:
             | Not sure I understand, Mac OS is BSD based.
             | https://en.wikipedia.org/wiki/Darwin_(operating_system)
        
               | bigyabai wrote:
               | macOS is XNU-based. There is BSD code that runs in the
               | microkernel level and BSD tools in the userland, but the
               | kernel does not resemble BSD's architecture or adopt
               | BSD's license.
               | 
               | This is an issue for some industry-standard software like
               | CUDA, which _does_ provide BSD drivers with ARM support
               | that just never get adopted by Apple:
               | https://www.nvidia.com/en-us/drivers/unix/
        
               | 7e wrote:
               | If there were TCO advantages with this setup, CUDA would
               | not be a blocker.
        
               | bigyabai wrote:
               | CUDA's just one example; there's a lot of hardware
               | support on the BSDs that Apple doesn't want to inherit.
        
               | ngcc_hk wrote:
               | Why maint other and have baggage ?
        
               | bigyabai wrote:
               | Because Apple already does...? There's still PowerPC and
               | MIPS code that runs in macOS. Asking for CUDA
               | compatibility is not somehow too hard for the trillion-
               | dollar megacorp to handle.
        
             | mjlee wrote:
             | Why? AWS manages to do it
             | (https://aws.amazon.com/ec2/instance-types/mac/). Smaller
             | companies too - https://macstadium.com
             | 
             | Having used both professionally, once you understand how to
             | drive Apple's MDM, Mac OS is as easy to sysadmin as Linux.
             | I'll grant you it's a steep learning curve, but so is
             | Linux/BSD if you're coming at it fresh.
             | 
             | In certain ways it's easier - if you buy a device through
             | Apple Business you can have it so that you (or someone
             | working in a remote location) can take it out of the shrink
             | wrap, connect it to the internet, and get a configured and
             | managed device automatically. No PXE boot, no disk imaging,
             | no having it shipped to you to configure and ship out
             | again. If you've done it properly the user can't
             | interrupt/corrupt the process.
             | 
             | The only thing they're really missing is an iLo, I can
             | imagine how AWS solved that, but I'd love to know.
        
           | api wrote:
           | No way buying a bunch of minis could be as efficient as much
           | denser GPU racks. You have to consider all the logistics and
           | power draw, and high end nVidia stuff and probably even AMD
           | stuff is faster than M series GPUs.
           | 
           | What this does offer is a good alternative to GPUs for
           | smaller scale use and research. At small scale it's probably
           | competitive.
           | 
           | Apple wants to dominate the pro and serious amateur niches.
           | Feels like they're realizing that local LLMs and AI research
           | is part of that, is the kind of thing end users would want
           | big machines to do.
        
             | gumboshoes wrote:
             | Exactly: The AI appliance market. A new kind of home or
             | small-business server.
        
               | jabbywocker wrote:
               | I'm expecting Apple to release a new Mac Pro in the next
               | couple years who's main marketing angle is exactly this
        
               | firecall wrote:
               | Seems like it could be a thing.
               | 
               | Also, I'm curious and in case anyone that knows reads
               | this comment:
               | 
               | Apple say they can't get the performance they want out of
               | discreet GPUs.
               | 
               | Fair enough. But yet nVidia becomes the most valuable
               | company in the world selling GPUs.
               | 
               | So...
               | 
               | Now I get that Apples use case is essentially sealed
               | consumer devices built with power consumption and
               | performance tradeoffs in mind.
               | 
               | But could Apple use its Apple Silicon tech to build a Mac
               | Pro with its own expandable GPU options?
               | 
               | Or even other brand GPUs knowing they would be used for
               | AI research etc.... If Apple ever make friends with
               | nVidia again of course :-/
               | 
               | What we know of Tim Cooks Apple is that it doesn't like
               | to leave money on the table, and clearly they are right
               | now!
        
               | jabbywocker wrote:
               | There's been rumors of Apple working on M-chips that have
               | the GPU and CPU as discrete chiplets. The original rumor
               | said this would happen with the M5 Pro, so it's
               | potentially on the roadmap.
               | 
               | Theoretically they could farm out the GPU to another
               | company but it seems like they're set on owning all of
               | the hardware designs.
        
               | nntwozz wrote:
               | Apple always strives for complete vertical integration.
               | 
               | SJ loved to quote Alan Kay:
               | 
               | "People who are really serious about software should make
               | their own hardware."
               | 
               | Qualcomm are the latest on the chopping block, history
               | repeating itself.
               | 
               | If I were a betting man I'd say Apple's never going back.
        
               | storus wrote:
               | TSMC has a new tech that allows seamless integration of
               | mini chiplets, i.e. you can add as many CPU/GPU cores in
               | mini chiplets as you wish and glue them seamlessly
               | together, at least in theory. The rumor is that TSMC had
               | some issues with it which is why M5P and M5M are delayed.
        
               | api wrote:
               | It's really the only common reason to buy a machine that
               | big these days. I could see a Mac Pro with a huge GPU and
               | up to a terabyte of RAM.
               | 
               | I guess there are other kinds of scientific simulation,
               | very large dev work, and etc., but those things are quite
               | a bit more niche.
        
               | pjmlp wrote:
               | I fear they no longer care about the workstation market,
               | even the folks at ATP Podcast are at the verge of
               | accepting it.
        
               | alwillis wrote:
               | > I'm expecting Apple to release a new Mac Pro in the
               | next couple years
               | 
               | I think Apple is done with expansion slots, etc.
               | 
               | You'll likely see M5 Mac Studios fairly soon.
        
             | FuckButtons wrote:
             | Power draw? A entire Mac Pro running flat out uses less
             | power than 1 5090. If you have a workload that needs a huge
             | memory footprint then the tco of the Macs, even with their
             | markup may be lower.
        
           | willtemperley wrote:
           | I think it's going to be great for smaller shops that want on
           | premise private cloud. I'm hoping this will be a win for in-
           | memory analytics on macOS.
        
         | CamperBob2 wrote:
         | Almost the most impressive thing about that is the power
         | consumption. ~50 watts for both of them? Am I reading it wrong?
        
           | wmf wrote:
           | Yeah, two Mac Studios is going to be ~400 W.
        
             | CamperBob2 wrote:
             | What am I missing? https://i.imgur.com/YpcnlCH.png
             | 
             | (Edit: interesting, thanks. So the underlying OS APIs that
             | supply the power-consumption figures reported by asitop are
             | just outright broken. The discrepancy is far too large to
             | chalk up to static power losses or die-specific calibration
             | factors that the video talks about.)
        
               | wmf wrote:
               | https://www.youtube.com/watch?v=zCkbVLqUedg
        
             | m-s-y wrote:
             | Can confirm. My M3 Ultra tops out at 210W when ComfyUI or
             | ollama is running flat out. Confirmed via smart plug.
        
         | anemll wrote:
         | Tensor Parallel test with RDMA last week
         | https://x.com/anemll/status/1996349871260107102
         | 
         | Note fast sync workaround
        
       | pstuart wrote:
       | I imagine that M5 Ultra with Thunderbolt 5 could be a decent
       | contender for building plug and play AI clusters. Not cheap, but
       | neither is Nvidia.
        
         | whimsicalism wrote:
         | nvidia is absolutely cheaper per flop
        
           | FlacksonFive wrote:
           | To acquire, maybe, but to power?
        
             | whimsicalism wrote:
             | machine capex currently dominates power
        
               | amazingman wrote:
               | Sounds like an ecosystem ripe for horizontally scaling
               | cheaper hardware.
        
               | crote wrote:
               | If I understand correctly, a big problem is that the
               | calculation isn't embarrasingly parallel: the various
               | chunks are _not_ independent, so you need to do a lot of
               | IO to get the results from step N from your neighbours to
               | calculate step N+1.
               | 
               | Using more smaller nodes means your cross-node IO is
               | going to explode. You might save money on your compute
               | hardware, but I wouldn't be surprised if you'd end up
               | with an even greater cost increase on the network
               | hardware side.
        
           | adastra22 wrote:
           | FLOPS are not what matters here.
        
             | whimsicalism wrote:
             | also cheaper memory bandwidth. where are you claiming that
             | M5 wins?
        
               | Infernal wrote:
               | I'm not sure where else you can get a half TB of 800GB/s
               | memory for < $10k. (Though that's the M3 Ultra, don't
               | know about the M5). Is there something competitive in the
               | nvidia ecosystem?
        
               | whimsicalism wrote:
               | I wasn't aware that M3 Ultra offered a half terabyte of
               | unified memory, but an RTX5090 has double that bandwidth
               | and that's before we even get into B200 (~8TB/s).
        
               | 650REDHAIR wrote:
               | You could get x1 M3 Ultra w/ 512gb of unified ram for the
               | price of x2 RTX 5090 totaling 64gb of vram not including
               | the cost of a rig capable of utilizing x2 RTX 5090.
        
               | bigyabai wrote:
               | Which would almost be great, if the M3 Ultra's GPU wasn't
               | ~3x weaker than a single 5090:
               | https://browser.geekbench.com/opencl-benchmarks
               | 
               | I don't think I can recommend the Mac Studio for AI
               | inference until the M5 comes out. And even then, it
               | remains to be seen how fast those GPUs are or if we even
               | get an Ultra chip at all.
        
               | adastra22 wrote:
               | Again, memory bandwidth is pretty much all that matters
               | here. During inference or training the CUDA cores of
               | retail GPUs are like 15% utilized.
        
               | my123 wrote:
               | Not for prompt processing. Current Macs are really not
               | great at long contexts
        
         | baq wrote:
         | at current memory prices today's _cheap_ is yesterday 's
         | _obscenely expensive_ - Apple 's current RAM upgrade prices are
         | cheap
        
       | jeffbee wrote:
       | Very cool. It requires a fully-connected mesh so the scaling
       | limit here would seem to be 6 Mac Studio M3 Ultra, up to 3TB of
       | unified memory to work with.
        
         | PunchyHamster wrote:
         | I'm sure someone will figure out how to make thunderbolt
         | switch/router
        
           | huslage wrote:
           | I don't believe the standard supports such a thing. But I
           | wonder if TB6 will.
        
             | kmeisthax wrote:
             | RDMA is a networking standard, it's supposed to be
             | switched. The reason why it's being done over Thunderbolt
             | is that it's the only cheap/prosumer I/O standard with
             | enough bandwidth to make this work. Like, 100Gbit Ethernet
             | cards are several hundred dollars minimum, for two ports,
             | _and_ you have to deal with SFP+ cabling. Thunderbolt is
             | just way nicer[0].
             | 
             | The way this capability is exposed in the OS is that the
             | computers negotiate an Ethernet bridge on top of the TB
             | link. I suspect they're actually exposing PCIe Ethernet
             | NICs to each other, but I'm not sure. But either way, a
             | "Thunderbolt router" would just be a computer with a
             | shitton of USB-C ports (in the same way that an "Ethernet
             | router" is just a computer with a shitton of Ethernet
             | ports). I suspect the biggest hurdle would actually just be
             | sourcing an SoC with a lot of switching fabric but not a
             | lot of compute. Like, you'd need Threadripper levels of
             | connectivity but with like, one or two actual CPU cores.
             | 
             | [0] Like, last time I had to swap work laptops, I just
             | plugged a TB cable between them and did an `rsync`.
        
               | bleepblap wrote:
               | I think you might be swapping RDMA with RoCE - RDMA can
               | happen entirely within a single node. For example between
               | an NVME and a GPU.
        
               | wmf wrote:
               | Within a single node it's just called DMA. RDMA is DMA
               | over a network and RoCE is RDMA over Ethernet.
        
               | bleepblap wrote:
               | Sorry, but it certainly isn't--
               | 
               | https://docs.nvidia.com/cuda/gpudirect-rdma/index.html
               | 
               | The "R" in RDMA means there are multiple DMA controllers
               | who can "transparently" share address spaces. You can
               | certainly share address spaces across nodes with RoCE or
               | Infiniband, but thats a layer on top
        
               | wmf wrote:
               | I'm going to agree to disagree with Nvidia here.
        
               | wtallis wrote:
               | I don't know why that NVIDIA document is wrong, but the
               | established term for doing DMA from eg. an NVMe SSD to a
               | GPU within a single system without the CPU initiating the
               | transfer is _peer to peer DMA_. RDMA is when your data
               | leaves the local machine 's PCIe fabric.
        
       | novok wrote:
       | Now we need some hardware that is rackmount friendly, an OS that
       | is not fidly as hell to manage in a data center or headless
       | server and we are off to the races! And no, custom racks are not
       | 'rackmount friendly'.
        
         | joeframbach wrote:
         | So, the Powerbook Duo Dock?
        
       | btown wrote:
       | It would be incredibly ironic if, with Apple's relatively stable
       | supply chain relative to the chaos of the RAM market these days
       | (projected to last for years), Apple compute became known as a
       | _cost-effective_ way to build medium-sized clusters for
       | inference.
        
         | andy99 wrote:
         | It's gonna suck if all the good Macs get gobbled up by
         | commercial users.
        
           | mschuster91 wrote:
           | it's not like regular people can afford this kind of Apple
           | machine anyway.
        
             | teeray wrote:
             | It's just depressing that the "PC in every home" era is
             | being rapidly pulled out from under our feet by all these
             | supply shocks.
        
               | dghlsakjg wrote:
               | Huh?
               | 
               | Home PCs are as cheap as they've ever been. Adjusted for
               | inflation the same can be said about "home use" Macs. The
               | list price of an entry level MacBook Air has been pretty
               | much the same for more than a decade. Adjust for
               | inflation, and you get a MacBook air for less than half
               | the real cost of the launch model that is massively
               | better in every way.
               | 
               | A blip in high end RAM prices has no bearing on
               | affordable home computing. Look at the last year or two
               | and the proliferation of cheap, moderately to highly
               | speced mini desktops.
               | 
               | I can get a Ryzen 7 system with 32gb of ddr5, and a 1tb
               | drive delivered to my house before dinner tomorrow for
               | $500 + tax.
               | 
               | That's not depressing, that's amazing!
        
               | heavyset_go wrote:
               | Home calculators are cheap as they've ever been, but this
               | era of computing is out of reach for the majority of
               | people.
               | 
               | The analogous PC for this era requires a large amount of
               | high speed memory and specialized inference hardware.
        
               | atonse wrote:
               | You can have access to a supercomputer for pennies,
               | internet access for very little money, and even an m4 Mac
               | mini for $500. You can have a raspberry pi computer for
               | even less. And buy a monitor for a couple hundred
               | dollars.
               | 
               | I feel like you're twisting the goalposts to make your
               | point that it has to be local compute to have access to
               | AI. Why does it need to be local?
               | 
               | Update: I take it back. You can get access to AI for
               | free.
        
               | dghlsakjg wrote:
               | What regular home workload are you thinking of that the
               | computer I described is incapable of?
               | 
               | You can call a computer a calculator, but that doesn't
               | make it a calculator.
               | 
               | Can they run SOTA LLMs? No. Can they run smaller, yet
               | still capable LLMs? Yes.
               | 
               | However, I don't think that the ability to run SOTA LLMs
               | is a reasonable expectation for "a computer in every
               | home" just a few years into that software category even
               | existing.
        
               | buu700 wrote:
               | It's kind of funny to see "a computer in every home"
               | invoked when we're talking about the equivalent of ~$100
               | buying a non-trivial percentage of all computational
               | power in existence at the time of the quote. By the
               | standards of that time, we don't just have a computer in
               | every home, we have a supercomputer in every pocket.
        
               | platevoltage wrote:
               | No it doesn't. The majority of people aren't trying to
               | run Ollama on their personal computers.
        
               | inferiorhuman wrote:
               | A blip in high end RAM prices
               | 
               | It's not a blip and it's not limited to high end machines
               | and configurations. Altman gobbled up the lion's share of
               | wafer production. Look at that Raspberry Pi article that
               | made it to the front page, that's pretty far from a high
               | end Mac and according to the article's author likely to
               | be exported from China due to the RAM supply crisis.
               | I can get a Ryzen 7 system with 32gb of ddr5, and a 1tb
               | drive delivered to my house       before dinner tomorrow
               | for $500 + tax.
               | 
               | B&H is showing a 7700X at $250 with their cheapest 32GB
               | DDR5 5200 sticks at $384. So you've already gone over
               | budget for just the memory and CPU. No motherboard, no
               | SSD.
               | 
               | Amazon is showing some no-name stuff at $298 as their
               | cheapest memory and a Ryzen 7700X at $246.
               | 
               | Add another $100 for an NVMe drive and another $70-100
               | for the cheapest AM5 motherboards I could find on either
               | of those sites.
        
               | dghlsakjg wrote:
               | People that can reliably predict the future, especially
               | when it comes to rising markets, are almost always
               | billionaires. It is a skill so rare that it can literally
               | make you the richest man on earth. Why should I trust
               | your prediction of future markets that this pricing is
               | the new standard, and will never go down? Line doesn't
               | always go up, even if it feels like it is right now, and
               | all the tech media darlings are saying so.
               | 
               | If everything remains the same, RAM pricing will also. I
               | have never once found a period in known history where
               | everything stays the same, and I would be willing to bet
               | 5 figures that at some point in the future I will be able
               | to buy DDR5 or better ram for cheaper than today. I can
               | point out that in the long run, prices for computing
               | equipment have always fallen. I would trust that trend a
               | lot more than a shortage a few months old changing the
               | very nature of commodity markets. Mind you, I'm not the
               | richest man on earth either, so my pattern matched
               | opinion should be judged the same.
               | 
               | > B&H is showing a 7700X at $250 with their cheapest 32GB
               | DDR5 5200 sticks at $384. So you've already gone over
               | budget for just the memory and CPU. No motherboard, no
               | SSD.
               | 
               | I didn't say I could build one from parts. Instead I said
               | buy a mini pc, and then went and looked up the specs and
               | price point to be sure.
               | 
               | The PC that I was talking about is
               | here[https://a.co/d/6c8Udbp]. I live in Canada so
               | translated the prices to USD. Remember that US stores are
               | sometimes forced to hide a massive import tax in those
               | parts prices. The rest of the world isn't subject to that
               | and pays less.
               | 
               | Edit: here's an equivalent speced pc available in the US
               | for $439 with a prime membership. So even with the cost
               | of prime membership you can get a Ryzen 7 32gb 1tb for
               | $455. https://www.amazon.com/BOSGAME-P3-Gigabit-Ethernet-
               | Computer/...
        
               | inferiorhuman wrote:
               | People that can reliably predict the future
               | 
               | You don't need to be a genius or a billionaire to realize
               | that when _most_ of the global supply of a product
               | becomes unavailable the remaining supply gets more
               | expensive.                 here's an equivalent speced pc
               | available in the US for $439 with a prime membership.
               | 
               | So with prime that's $439+139 for $578 which is only
               | slightly higher than the cost without prime of $549.99.
        
               | dghlsakjg wrote:
               | > You don't need to be a genius or a billionaire to
               | realize that when most of the global supply of a product
               | becomes unavailable the remaining supply gets more
               | expensive.
               | 
               | Yes. Absolutely correct if you are talking about the
               | short term. I was talking about the long term, and said
               | that. If you are so certain would you take this bet: any
               | odds, any amount that within 1 month I can buy 32gb of
               | new retail DDR5 in the US for at least 10% less than the
               | $384 you cited. (think very hard on why I might offer you
               | infinite upside so confidently. It's not because I know
               | where the price of RAM is going in the short term)
               | 
               | > So with prime that's $439+139 for $578 which is only
               | slightly higher than the cost without prime of $549.99.
               | 
               | At this point I can't tell if you are arguing in bad
               | faith, or just unfamiliar with how prime works. Just in
               | case: You have cited the cost of prime for a full year.
               | You can buy just a month of prime for a maximum price of
               | $14.99 (that's how I got $455) if you have already used
               | your free trial, and don't qualify for any discounts.
               | Prime also allows cancellation within 14 days of signing
               | up for a paid option, which is more than enough time to
               | order a computer, and have it delivered, and cancel for a
               | full refund.
               | 
               | So really, if you use a trial or ask for a refund for
               | your prime fees the price is $439. So we have actually
               | gotten the price a full 10% lower than I originally
               | cited.
               | 
               | Edit: to eliminate any arguments about Prime in the price
               | of the PC, here's an indentically speced mini PC for the
               | same price from Newegg
               | https://www.newegg.com/p/2SW-00BM-00002
        
               | r0b05 wrote:
               | What is your estimate for when memory prices will
               | decrease?
               | 
               | I agree that we've seen similar fluctuations in the past
               | and the price of compute trends down in the long-term.
               | This could be a bubble, which it likely is, in which case
               | prices should return to baseline eventually. The
               | political climate is extremely challenging at this time
               | though so things could take longer to stabilize. Do you
               | think we're in this ride for months or years?
        
               | dghlsakjg wrote:
               | I can't be more clear: specificity around predicting the
               | future is close to impossible. There are 9 figure bets on
               | both sides of the RAM issue, and strategic national
               | concerns. I say that prices will go down at some point in
               | the future for reasons highlighted already, but I have no
               | clue when. Keep in mind what I myself have said about
               | human ability to predict the future. You would be a fool
               | to believe anyone's specific estimates.
               | 
               | Maybe the AI money train stops after Christmas. The
               | entire economy is fucked, but RAM is cheap.
               | 
               | Maybe we unlock AGI and the price sky rockets further
               | before factories can get built.
               | 
               | There are just too many variables.
               | 
               | The real test is if someone had seen this coming, they
               | would have made massive absurd investment returns just by
               | buying up stock and storing it for a few months. Anyone
               | who didn't take advantage of that opportunity has proved
               | that they had no real confidence in their ability to
               | predict the future price of RAM. RAM inventory might have
               | been one of the highest return investments possible this
               | year. Where are all the RAM whales in Lambos who saw this
               | coming?
               | 
               | As a corollary: we can say that unless you have some skin
               | in the game and have invested a significant amount of
               | your wealth in RAM chips, then you don't know which way
               | the price is going or when.
               | 
               | Extending that even further: people complaining about RAM
               | prices being so high, and moaning that they bought less
               | RAM because of it are actually signaling through action
               | that they think that prices will go down or have leveled
               | off. Anyone who believes that sticks of DDR5 RAM will
               | continue the trend should be cleaning out Amazon, Best
               | Buy and Newegg since the price will never be lower than
               | today.
               | 
               | The distinct lack of serious people saying "I told ya so"
               | with receipts, combined with the lack of people hoarding
               | RAM to sell later is a good indirect signal that no one
               | knows what is happening in the near term.
        
               | SunlitCat wrote:
               | Don't forget that many of these manufacturers operate
               | with long-term supply contracts for components like RAM,
               | maintain existing inventory, or are selling systems that
               | were produced some time ago. That helps explain why we
               | are still seeing comparatively low prices at the moment.
               | 
               | If the current RAM supply crisis continues, it is very
               | likely that these kinds of offers will disappear and that
               | systems like this will become more expensive as well, not
               | to mention all the other products that rely on DRAM
               | components.
               | 
               | I also don't believe RAM prices will drop again anytime
               | soon, especially now that manufacturers have seen how
               | high prices can go while demand still holds. Unlike
               | something like graphics cards, RAM is not optional, it is
               | a fundamental requirement for building any computer (or
               | any device that contains one). People don't buy it
               | because they want to, but because they have to.
               | 
               | In the end, I suspect that some form of market-regulating
               | mechanism may be required, potentially through government
               | intervention. Otherwise, it's hard for me to see what
               | would bring prices down again, unless Chinese
               | manufacturers manage to produce DRAM at scale, at
               | significantly lower cost, and effectively flood the
               | market.
        
               | sspiff wrote:
               | Add to that a case, PSU and monitor and you're
               | realitically over $1000
        
               | behnamoh wrote:
               | > Home PCs are as cheap as they've ever been.
               | 
               | just the 5090 GPU costs +$3k, what are you even talking
               | about
        
               | pests wrote:
               | A home PC has to have a SOTA gpu?
        
               | morshu9001 wrote:
               | Probably upset that the high-end video game "hobby" costs
               | more than it used to. Used to be $1-2K for the very best
               | gaming GPU of the time.
        
               | dghlsakjg wrote:
               | "A computer in every home" (from the original post I was
               | replying to) does not mean "A computer with the highest
               | priced version of the highest priced optional accessory
               | for computers in every home"
               | 
               | I'm talking about the hundreds of affordable models that
               | are perfectly suitable for everything up to and including
               | AAA gaming.
               | 
               | The existence of expensive, and very much optional, high
               | end computer parts does not mean that affordable
               | computers are not more incredible than ever.
               | 
               | Just because cutting edge high end parts are out of reach
               | to you, does not mean that perfectly usable computers are
               | too, as I demonstrated with actual specs and prices in my
               | post.
               | 
               | That's what I'm talking about.
        
               | platevoltage wrote:
               | Man you positively demolished that straw man.
               | 
               | How much as a base model MacBook Air changed in price
               | over the last 15 years? With inflation, it's gotten
               | cheaper.
        
               | dghlsakjg wrote:
               | Some numbers to drive your point home:
               | 
               | The original base MacBook Air sold for $1799 in 2008. The
               | inflation adjusted price is $2715.
               | 
               | The current base model is $999, and literally better in
               | every way except thickness on one edge.
               | 
               | If we constrain ourselves to just 15 years. The $999 MBA
               | was released 15 years ago ($1488 in real dollars). The
               | list price has remained the same for the base model, with
               | the exception of when they sold the discontinued 11" MBAs
               | for $899.
               | 
               | It's actually kind of wild how much better and cheaper
               | computers have gotten.
        
               | morshu9001 wrote:
               | It's also gotten cheaper nominally. I just got a new base
               | MBA for $750. Kinda surprised, like there has to be some
               | catch.
        
               | teaearlgraycold wrote:
               | I feel bad for their competitors. We need good
               | competition in the long run but over the last few years
               | it's made less and less sense to get something other than
               | an Apple laptop for most use cases.
        
               | jeroenhd wrote:
               | > I can get a Ryzen 7 system with 32gb of ddr5, and a 1tb
               | drive delivered to my house before dinner tomorrow for
               | $500 + tax
               | 
               | That's an amazing price, but I'd like to see where you're
               | getting it. 32GB of RAM alone costs EUR450 here (EUR250
               | if you're willing to trust Amazon's February 2026
               | delivery dates).
               | 
               | Getting a PC isn't that expensive, but after the
               | blockchain hype and then the AI hype, prices have yet to
               | come down. All estimations I've seen will have RAM prices
               | increase further until the summer of next year, and the
               | first dents in pricing coming the year after at the very
               | earliest.
        
               | dghlsakjg wrote:
               | Amazon[0] link below. Equivalent systems also available
               | at Newegg for the same price since someone nitpicked that
               | you need a $15 prime membership to get that Amazon deal.
               | 
               | Shipping might screw you but here's in stock 32gb kits of
               | name brand RAM from a well known retailer in the US for
               | $280[1].
               | 
               | Edit: same crucial RAM kit is 220GBP in stock at
               | amazon[2]
               | 
               | (0)https://www.amazon.com/BOSGAME-P3-Gigabit-Ethernet-
               | Computer/...
               | 
               | (1)https://www.bhphotovideo.com/c/product/1809983-REG/cru
               | cial_c...
               | 
               | (2) https://www.amazon.co.uk/dp/B0CTHXMYL8?tag=pcp0f-21&l
               | inkCode...
        
               | Aurornis wrote:
               | You can get a Mac Mini for $600 with 16GB of RAM and it
               | will be more powerful than the "PC in every home" people
               | would need for any common software.
               | 
               | The personal computing situation is great right now. RAM
               | is temporarily more expensive, but it's definitely not
               | ending any eras.
        
               | m-s-y wrote:
               | Not Apple's ram.
        
               | jeroenhd wrote:
               | RAM prices have exploded enough that Apple's RAM is now
               | no longer a bad deal. At least until their next price
               | hikes.
               | 
               | We're going back to the "consumer PCs have 8GB of RAM
               | era" thanks to the AI bubble.
        
               | RestartKernel wrote:
               | Funny, considering Macbooks finally started shipping at
               | 16 GB due to Apple Intelligence.
        
           | icedchai wrote:
           | Outside of YouTube influencers, I doubt many home users are
           | buying a 512G RAM Mac Studio.
        
             | FireBeyond wrote:
             | I doubt many of them are, either.
             | 
             | When the 2019 Mac Pro came out, it was "amazing" how many
             | _still photography_ YouTubers all got launch day deliveries
             | of the same BTO Mac Pro, with _exactly_ the same spec:
             | 
             | 18 core CPU, 384GB memory, Vega II Duo GPU and an 8TB SSD.
             | 
             | Or, more likely, Apple worked with them and made sure each
             | of them had this Mac on launch day, while they waited for
             | the model they _actually ordered_. Because they sure as
             | hell didn 't need an $18,000 computer for Lightroom.
        
               | lukeh wrote:
               | Still rocking a 2019 Mac Pro with 192GB RAM for audio
               | work, because I need the slots and I can't justify the
               | expense of a new one. But I'm sure a M4 Mini is faster.
        
               | NSUserDefaults wrote:
               | How crazy do you have to get with # of tracks or plugins
               | before it starts to struggle? I was under the impression
               | that most studios would be fine with an Intel Mac Mini +
               | external storage.
        
             | DrStartup wrote:
             | I'm neither and have 2. 24/7 async inference against github
             | issues. Free. (once you buy the macs that is)
        
               | Waterluvian wrote:
               | I wonder what the actual lifetime amortized cost will be.
        
               | oidar wrote:
               | Every time I'm tempted to get one of these beefy mac
               | studios, I just calculate how much inference I can buy
               | for that amount and it's never a good deal.
        
               | bee_rider wrote:
               | Are the inference providers profitable yet? Might be nice
               | to be ready for the day when we see the real price of
               | their services.
        
               | Nextgrid wrote:
               | Isn't it then even better to enjoy cheap inference thanks
               | to techbro philanthropy while it lasts? You can always
               | buy the hardware once the free money runs out.
        
               | bee_rider wrote:
               | Probably depends on what you are interested in. IMO,
               | setting up local programs is more fun anyway. Plus, any
               | project I'd do with LLMs would just be for fun and
               | learning at this point, so I figure it is better to learn
               | skills that will be useful in the long run.
        
               | embedding-shape wrote:
               | Every time someone brings up that, it brings me back
               | memories of trying to frantically finish stuff as quickly
               | as possible as either my quota slowly go down with each
               | API request, or the pay-as-you-go bill is increasing 0.1%
               | for each request.
               | 
               | Nowadays I fire off async jobs that involve 1000s of
               | requests, billion of tokens, yet it costs basically the
               | same as if I didn't.
               | 
               | Maybe it takes a different type of person, than the one I
               | am, but all these "pay-as-you-go"/tokens/credits
               | platforms make me nervous to use, and I end up not using
               | it or spending time trying to "optimize", while investing
               | in hardware and infrastructure I can run at home and use
               | that seems to be no problem for my head to just roll
               | with.
        
               | noname120 wrote:
               | But the downside is that you are stuck with inferior
               | LLMs. None of the best models have open weights: Gemini
               | 3.5, Claude Sonnet/Opus 4.5, ChatGPT 5.2. The best model
               | with open weights performs an order of magniture worse
               | than those.
        
               | embedding-shape wrote:
               | The best weights are the weights you can train yourself
               | for specific use cases. As long as you have the data and
               | the infrastructure to train/fine-tune your own small
               | models, you'll get drastically better results.
               | 
               | And just because you're mostly using local models doesn't
               | mean you can't use API hosted models in specific
               | contexts. Of course, then the same dread sets in, but if
               | you can do 90% of the tokens with local models and 10%
               | with pay-per-usage API hosted models, you get the best of
               | both worlds.
        
               | asimovDev wrote:
               | anyone buying these is usually more concerned with just
               | being able to run stuff on their own terms without
               | handing their data off. otherwise it's probably always
               | cheaper to rent compute for intense stuff like this
        
               | dontlaugh wrote:
               | For now, while everything you can rent is sold at a loss.
        
               | stingraycharles wrote:
               | Nevermind the fact that there are a lot of high quality
               | (the highest quality?) models that are not released as
               | open source.
        
               | icedchai wrote:
               | Heh. I'm jealous. I'm still running a first gen Mac
               | Studio (M1 Max, 64 gigs RAM.) It seemed like a beast only
               | 3 years ago.
        
               | madeofpalk wrote:
               | I'm not sure who 'home users' are, but i doubt they're
               | buying two $9,499 computers.
        
               | trvz wrote:
               | Peanuts for people who make their living with computers.
        
               | jon-wood wrote:
               | So, not a home user then. If you make your living with
               | computers in that manner you are by definition a
               | professional, and just happen to have your work hardware
               | at home.
        
               | servercobra wrote:
               | Interesting. Answering them? Solving them? Looking for
               | ones to solve?
        
             | mirekrusin wrote:
             | Of course they're not. Everybody is waiting for next
             | generation that will run LLMs faster to start buying.
        
               | rbanffy wrote:
               | Every generation runs LLMs faster than the previous one.
        
             | 7e wrote:
             | That product can still steal fab slots from cheaper, more
             | prosumer products.
        
             | kridsdale1 wrote:
             | I did. Admittedly it was for video processing at 8k which
             | uses more than 128gb of ram, but I am NOT a YouTuber.
        
         | teaearlgraycold wrote:
         | It already is depending on your needs.
        
       | timsneath wrote:
       | Also see https://www.engadget.com/ai/you-can-turn-a-cluster-of-
       | macs-i...
        
       | geerlingguy wrote:
       | This implies you'd run more than one Mac Studio in a cluster, and
       | I have a few concerns regarding Mac clustering (as someone who's
       | managed a number of tiny clusters, with various hardware):
       | 
       | 1. The power button is in an awkward location, meaning
       | rackmounting them (either 10" or 19" rack) is a bit cumbersome
       | (at best)
       | 
       | 2. Thunderbolt is great for peripherals, but as a semi-permanent
       | interconnect, I have worries over the port's physical
       | stability... wish they made a Mac with QSFP :)
       | 
       | 3. Cabling will be important, as I've had tons of issues with TB4
       | and TB5 devices with anything but the most expensive Cable
       | Matters and Apple cables I've tested (and even then...)
       | 
       | 4. macOS remote management is not nearly as efficient as Linux,
       | at least if you're using open source / built-in tooling
       | 
       | To that last point, I've been trying to figure out a way to, for
       | example, upgrade to macOS 26.2 from 26.1 remotely, without a GUI,
       | but it looks like you _have_ to use something like Screen Sharing
       | or an IP KVM to log into the UI, to click the right buttons to
       | initiate the upgrade.
       | 
       | Trying "sudo softwareupdate -i -a" will install minor updates,
       | but not full OS upgrades, at least AFAICT.
        
         | eurleif wrote:
         | I have no experience with this, but for what it's worth, looks
         | like there's a rack mounting enclosure available which
         | mechanically extends the power switch:
         | https://www.sonnetstore.com/products/rackmac-studio
        
           | geerlingguy wrote:
           | I have something similar from MyElectronics, and it works,
           | but it's a bit expensive, and still imprecise. At least the
           | power button isn't in the back corner underneath!
        
         | wlesieutre wrote:
         | For #2, OWC puts a screw hole above their dock's thunderbolt
         | ports so that you can attach a stabilizer around the cord
         | 
         | https://www.owc.com/solutions/thunderbolt-dock
         | 
         | It's a poor imitation of old ports that had screws on the
         | cables, but should help reduce inadvertent port stress.
         | 
         | The screw only works with limited devices (ie not the Mac
         | Studio end of the cord) but it can also be adhesive mounted.
         | 
         | https://eshop.macsales.com/item/OWC/CLINGON1PK/
        
           | crote wrote:
           | That screw hole is just the regular locking USB-C variant, is
           | it not?
           | 
           | See for example:
           | 
           | https://www.startech.com/en-jp/cables/usb31cctlkv50cm
        
             | wlesieutre wrote:
             | Looks like it! Thanks for pointing this out, I had no idea
             | it was a standard.
             | 
             | Apparently since 2016 https://www.usb.org/sites/default/fil
             | es/documents/usb_type-c...
             | 
             | So for any permanent Thunderbolt GPU setups, they should
             | really be using this type of cable
        
               | wtallis wrote:
               | Note that the locking connector OWC uses is _a_ standard,
               | not _the_ standard. This is USB we 're dealing with, so
               | they made it messy: the spec defines two different
               | mutually-incompatible locking mechanisms.
        
               | jamiek88 wrote:
               | Of course they do.
        
             | TheJoeMan wrote:
             | Now that's one way to enforce not inserting a USB upside-
             | down.
        
         | timc3 wrote:
         | It's been terrible for years/forever. Even Xserves didn't
         | really meet the needs of a professional data centre. And it's
         | got worse as a server OS because it's not a core focus. Don't
         | understand why anyone tries to bother - apart from this MLX use
         | case or as a ProRes render farm.
        
           | crote wrote:
           | iOS build runner. Good luck developing cross-platform apps
           | without a Mac!
        
             | jeroenhd wrote:
             | Practically, just run the macos-inside-kvm-inside-docker
             | command. Not very fast, but you can compile the entire
             | thing outside of the VM, all you need is the final
             | incantations to get Apple's signatures on there.
             | 
             | Legally, you probably need a Mac. Or rent access to one,
             | that's probably cheaper.
        
         | colechristensen wrote:
         | There are open source MDM projects, I'm not familiar but
         | https://github.com/micromdm/nanohub might do the job for OS
         | upgrades.
        
         | rsync wrote:
         | "... Thunderbolt is great for peripherals, but as a semi-
         | permanent interconnect, I have worries over the port's physical
         | stability ..."
         | 
         | Thunderbolt as a server interconnect displeases me
         | _aesthetically_ but my conclusion is the opposite of yours:
         | 
         | If the systems are locked into place as servers in a rack the
         | movements and stresses on the cable are much lower than when it
         | is used as a peripheral interconnect for a desktop or laptop,
         | yes ?
        
           | 827a wrote:
           | This is a semi-solved problem e.g.
           | https://www.sonnetstore.com/products/thunderlok-a
           | 
           | Apple's chassis do not support it. But conceptually that's
           | not a Thunderbolt problem, it's an Apple problem. You could
           | probably drill into the Mac Studio chassis to create mount
           | points.
        
             | broretore wrote:
             | You could also epoxy it.
        
         | badc0ffee wrote:
         | > To that last point, I've been trying to figure out a way to,
         | for example, upgrade to macOS 26.2 from 26.1 remotely,
         | 
         | I think you can do this if you install a MDM profile on the
         | Macs and use some kind of management software like Jamf.
        
         | 827a wrote:
         | They do still sell the Mac Pro in a rack mount configuration.
         | But, it was never updated for M3 Ultra, and feels not long for
         | this world.
        
         | ThomasBb wrote:
         | With MDM solutions you can not only get software update
         | management, but even full LOM for models that support this.
         | There are free and open source MDM out there.
        
         | cromniomancer wrote:
         | VNC over SSH tunneling always worked well for me before I had
         | Apple Remote Desktop available, though I don't recall if I ever
         | initiated a connection attempt from anything other than
         | macOS...
         | 
         | erase-install can be run non-interactively when the correct
         | arguments are used. I've only ever used it with an MDM in play
         | so YMMV:
         | 
         | https://github.com/grahampugh/erase-install
        
       | givemeethekeys wrote:
       | Would this also work for gaming?
        
         | AndroTux wrote:
         | No
        
       | storus wrote:
       | Is there any way to connect DGX Sparks to this via USB4? Right
       | now only 10GbE can be used despite both Spark and MacStudio
       | having vastly faster options.
        
         | zackangelo wrote:
         | Sparks are built for this and actually have Connect-X 7 NICs
         | built in! You just need to get the SFPs for them. This means
         | you can natively cluster them at 200Gbps.
        
           | wtallis wrote:
           | That doesn't answer the question, which was how to get a
           | high-speed interconnect between a Mac and a DGX Spark. The
           | most likely solution would be a Thunderbolt PCIe enclosure
           | and a 100Gb+ NIC, and passive DAC cables. The tricky part
           | would be macOS drivers for said NIC.
        
             | zackangelo wrote:
             | You're right I misunderstood.
             | 
             | I'm not sure if it would be of much utility because this
             | would presumably be for tensor parallel workloads. In that
             | case you want the ranks in your cluster to be uniform or
             | else everything will be forced to run at the speed of the
             | slowest rank.
             | 
             | You could run pipeline parallel but not sure it'd be that
             | much better than what we already have.
        
               | storus wrote:
               | It was about this use case:
               | 
               | https://blog.exolabs.net/nvidia-dgx-spark/
        
       | daft_pink wrote:
       | Hoping Apple has secured plentiful DDR5 to use in their machines
       | so we can buy M5 chips with massive amounts of RAM soon.
        
         | colechristensen wrote:
         | Apple tends to book its fab time / supplier capacity years in
         | advance
        
           | lossolo wrote:
           | I hope so, I want to replace my M1 Pro with MacBook Pro with
           | M5 Pro when they release it next year.
        
             | colechristensen wrote:
             | I mostly want the M5 Pro because my choice of an M4 Air
             | this year with 24 GB of RAM is turning out to be less than
             | I want with the things I'm doing these days.
        
       | reaperducer wrote:
       | As someone not involved in this space at all, is this similar to
       | the old MacOS Xgrid?
       | 
       | https://en.wikipedia.org/wiki/Xgrid
        
         | wmf wrote:
         | No.
        
       | reilly3000 wrote:
       | dang I wish I could share md tables.
       | 
       | Here's a text edition: For $50k the inference hardware market
       | forces a trade-off between capacity and throughput:
       | 
       | * Apple M3 Ultra Cluster ($50k): Maximizes capacity (3TB). It is
       | the only option in this price class capable of running 3T+
       | parameter models (e.g., Kimi k2), albeit at low speeds (~15 t/s).
       | 
       | * NVIDIA RTX 6000 Workstation ($50k): Maximizes throughput (>80
       | t/s). It is superior for training and inference but is hard-
       | capped at 384GB VRAM, restricting model size to <400B parameters.
       | 
       | To achieve both high capacity (3TB) and high throughput (>100
       | t/s) requires a ~$270,000 NVIDIA GH200 cluster and data center
       | infrastructure. The Apple cluster provides 87% of that capacity
       | for 18% of the cost.
        
         | mechagodzilla wrote:
         | You can keep scaling down! I spent $2k on an old dual-socket
         | xeon workstation with 768GB of RAM - I can run Deepseek-R1 at
         | ~1-2 tokens/sec.
        
           | ternus wrote:
           | And if you get bored of that, you can flip the RAM for more
           | than you spent on the whole system!
        
           | Weryj wrote:
           | Just keep going! 2TB of swap disk for 0.0000001 t/sec
        
             | kergonath wrote:
             | Hang on, starting benchmarks on my Raspberry Pi.
        
               | euroderf wrote:
               | By the year 2035, toasters will run LLMs.
        
               | pickle-wizard wrote:
               | On a lark a friend setup Ollama on a 8GB Raspberry Pi
               | with one of the smaller models. It worked by it was very
               | slow. IIRC it did 1 token/second.
        
           | a012 wrote:
           | And heat the whole house in parallel
        
           | jacquesm wrote:
           | I did the same, then put in 14 3090's. It's a little bit
           | power hungry but fairly impressive performance wise. The
           | hardest parts are power distribution and riser cards but I
           | found good solutions for both.
        
             | r0b05 wrote:
             | I think 14 3090's are more than a little power hungry!
        
               | jacquesm wrote:
               | to the point that I had to pull an extra circuit... but
               | tri phase so good to go even if I would like to go
               | bigger.
               | 
               | I've limited power consumption to what I consider the
               | optimum, each card will draw ~275 Watts (you can very
               | nicely configure this on a per-card basis). The server
               | itself also uses some for the motherboard, the whole rig
               | is powered from 4 1600W supplies, the gpus are divided
               | 5/5/4 and the mother board is connected to its own
               | supply. It's a bit close to the edge for the supplies
               | that have five 3090's on them but so far it held up quite
               | well, even with higher ambient temps.
               | 
               | Interesting tidbit: at 4 lanes/card throughput is barely
               | impacted, 1 or 2 is definitely too low. 8 would be great
               | but the CPUs don't have that many lanes.
               | 
               | I also have a threadripper which should be able to handle
               | that much RAM but at current RAM prices that's not
               | interesting (that server I could populate with RAM that I
               | still had that fit that board, and some more I bought
               | from a refurbisher).
        
               | nonplus wrote:
               | What pcie version are you running? Normally I would not
               | mention one of these, but you have already invested in
               | all the cards, and it could free up some space if any of
               | your lanes being used now are 3.0.
               | 
               | If you can afford the 16 (pcie 3) lanes, you could get a
               | PLX ("PCIe Gen3 PLX Packet switch X16 - x8x8x8x8" on ebay
               | for like $300) and get 4 of your cards up to x8.
        
               | jacquesm wrote:
               | All are PCIe 3.0, I wasn't aware of those switches at
               | all, in spite of buying my risers and cables from that
               | source! Unfortunately all of the slots on the board are
               | x8, there are no x16 slots at all.
               | 
               | So that switch would probably work but I wonder how big
               | the benefit would be: you will probably see effectively
               | an x4 -> (x4 / x8) -> (x8 / x8) -> (x8 / x8) -> (x8 / x4)
               | -> x4 pipeline, and then on to the next set of four
               | boards.
               | 
               | It might run faster on account of the three passes that
               | are are double the speed they are right now as long as
               | the CPU does not need to talk to those cards and all
               | transfers are between layers on adjacent cards (very
               | likely), and with even more luck (due to timing and lack
               | of overlap) it might run the two x4 passes at approaching
               | x8 speeds as well. And then of course you need to do this
               | a couple of times because four cards isn't enough, so
               | you'd need four of those switches.
               | 
               | I have not tried having a single card with fewer lanes in
               | the pipeline but that should be an easy test to see what
               | the effect on throughput of such a constriction would be.
               | 
               | But now you have me wondering to what extent I could
               | bundle 2 x8 into an x16 slot and then to use four of
               | these cards inserted into a fifth! That would be an
               | absolutely unholy assembly but it has the advantage that
               | you will need far fewer risers, just one x16 to x8/x8 run
               | in reverse (which I have no idea if that's even possible
               | but I see no reason right away why it would not work
               | unless there are more driver chips in between the slots
               | and the CPUs, which may be the case for some of the
               | farthest slots).
               | 
               | PCIe is quite amazing in terms of the topology tricks
               | that you can pull off with it, and c-payne's stuff is
               | extremely high quality.
        
             | tucnak wrote:
             | You get occasional accounts of 3090 home-superscalers
             | whereas they would put up eight, ten, fourteen cards. I
             | normally attribute this to obsessive-compulsive behaviour.
             | What kind of motherboard you ended up using and what's the
             | bi-directional bandwidth you're seeing? Something tells me
             | you're not using EPYC 9005's with up to 256x PCIe 5.0 lanes
             | per socket or something... Also: I find it hard to believe
             | the "performance" claims, when your rig is pulling 3 kW
             | from the wall (assuming undervolting at 200W per card?) The
             | electricity costs alone would surely make this intractable,
             | i.e. the same as running six washing machines all at once.
        
               | jacquesm wrote:
               | I love your skepsis of what I consider to be a fairly
               | normal project, this is not to brag, simply to document.
               | 
               | And I'm way above 3 kW, more likely 5000 to 5500 with the
               | GPUs running as high as I'll let them, or thereabouts,
               | but I only have one power meter and it maxes out at 2500
               | watts or so. This is using two Xeons in a very high end
               | but slightly older motherboard. When it runs the space
               | that it is in becomes hot enough that even in the winter
               | I have to use forced air from outside otherwise it will
               | die.
               | 
               | As for electricity costs, I have 50 solar panels and on a
               | good day they more than offset the electricity use, at 2
               | pm (solar noon here) I'd still be pushing 8 KW extra back
               | into the grid. This obviously does not work out so
               | favorably in the winter.
               | 
               | Building a system like this isn't very hard, it is just a
               | lot of money for a private individual but I can afford
               | it, I think this build is a bit under $10K, so a fraction
               | of what you'd pay for a commercial solution but obviously
               | far less polished and still less performant. But it is a
               | lot of bang for the buck and I'd much rather have this
               | rig at $10K than the first commercial solution available
               | at a multiple of this.
               | 
               | I wrote a bit about power efficiency in the run-up to
               | this build when I only had two GPUs to play with:
               | 
               | https://jacquesmattheij.com/llama-energy-efficiency/
               | 
               | My main issue with the system is that it is physically
               | fragile, I can't transport it at all, you basically have
               | to take it apart and then move the parts and re-assemble
               | it on the other side. It's just too heavy and the power
               | distribution is messy so you end up with a lot of loose
               | wires and power supplies. I _could_ make a complete
               | enclosure for everything but this machine is not running
               | permanently and when I need the space for other things I
               | just take it apart, store the GPUs in their original
               | boxes until the next home-run AI project. Putting it all
               | together is about 2 hours of work. We call it Frankie, on
               | account of how it looks.
               | 
               | edit: one more note, the noise it makes is absolutely
               | incredible and I would not recommend running something
               | like this in your house unless you are (1) crazy or (2)
               | have a separate garage where you can install it.
        
           | rpastuszak wrote:
           | Nice! What do you use it for?
        
             | mechagodzilla wrote:
             | 1-2 tokens/sec is perfectly fine for 'asynchronous'
             | queries, and the open-weight models are pretty close to
             | frontier-quality (maybe a few months behind?). I frequently
             | use it for a variety of research topics, doing feasibility
             | studies for wacky ideas, some prototypy coding tasks. I
             | usually give it a prompt and come back half an hour later
             | to see the results (although the thinking traces are
             | sufficiently entertaining that sometimes it's fun to just
             | read as it comes out). Being able to see the full thinking
             | traces (and pause and alter/correct them if needed) is one
             | of my favorite aspects of being able to run these models
             | locally. The thinking traces are frequently just as or more
             | useful than the final outputs.
        
         | icedchai wrote:
         | For $50K, you could buy 25 Framework desktop motherboards (128G
         | VRAM each w/Strix Halo, so over 3TB total) Not sure how you'll
         | cluster all of them but it might be fun to try. ;)
        
           | 3abiton wrote:
           | You could use llama.cpp rpc mode over "network" via
           | usb4/thunderbolt connection
        
           | sspiff wrote:
           | There is no way to achieve a high throughput low latency
           | connection between 25 Strix Halo systems. After accounting
           | for storage and network, there are barely any PCIe lanes left
           | to link two of them together.
           | 
           | You might be able to use USB4 but unsure how the latency is
           | for that.
        
             | icedchai wrote:
             | I figured, but it's good to have confirmation.
        
             | bee_rider wrote:
             | Do they need fast storage, in this application? Their OS
             | could be on some old SATA drive or whatever. The whole goal
             | is to get them on a fast network together; the models could
             | be stored on some network filesystem as well, right?
        
               | pests wrote:
               | It's more than just the model weights. During inference
               | there would be a lot of cross-talk as each node
               | broadcasts its results and gathers up what it needs from
               | the others for the next step.
        
             | 0manrho wrote:
             | In general I agree with you, the IO options exposed by
             | Strix Halo are pretty limited, but if we're getting
             | technical you can tunnel PCIe over USB4v2 _by the spec_ in
             | a way that 's functionally similar to Thunderbolt 5. That
             | gives you essentially 3 sets of native PCIe4x4 from the
             | chipset and an additional 2 sets tunnelled over USB4v2. TB5
             | and USB4 controllers are not made equal, so _in practice_
             | YMMV. Regardless of USB4v2 or TB5, you 'll take a minor
             | latency hit.
             | 
             | Strix Halo IO topology: https://www.techpowerup.com/cpu-
             | specs/ryzen-ai-max-395.c3994
             | 
             | Frameworks mainboard implements 2 of those PCIe4x4 GPP
             | interfaces as M.2 PHY's which you can use a passive adapter
             | to connect a standard PCIe AIC (like a NIC or DPU) to, and
             | also interestingly exposes that 3rd x4 GPP as a standard x4
             | length PCIe CEM slot, though the system/case isn't
             | compatible with actually installing a standard PCIe add in
             | card in there without getting hacky with it, especially as
             | it's not an open-ended slot.
             | 
             | You absolutely could slap 1x SSD in there for local
             | storage, and then attach up to 4x RDMA supporting NIC's to
             | a RoCE enabled switch (or Infiniband if you're feeling
             | special) to build out a Strix Halo cluster (and you could
             | do similar with Mac Studio's to be fair). You could get
             | really _extra_ by using a DPU /SmartNIC that allows you to
             | boot from a NVMeoF SAN to leverage all 5 sets of PCIe4x4
             | for connectivity without any local storage but we're
             | hitting a complexity/cost threshold with that that I doubt
             | most people want to cross. Or if they are willing to cross
             | that threshold, they'd also be looking at other solutions
             | better suited to that that don't require as many
             | workarounds.
             | 
             | Apple's solution is better for a small cluster, both in
             | pure connectivity terms and also with respect to it's
             | memory advantages, but Strix Halo is _doable_. However, in
             | both cases, scaling up beyond 3 or especially 4 nodes you
             | rapidly enter complexity and cost territory that is better
             | served by nodes that are less restrictive unless you have
             | some _very_ niche reason to use either Mac 's (especially
             | non-pro) or Strix Halo specifically.
        
         | FuckButtons wrote:
         | Are you factoring in the above comment about as yet un-
         | implemented parallel speed up in there? For on prem inference
         | without any kind of asic this seems quite a bargain relatively
         | speaking.
        
         | conradev wrote:
         | Apple deploys LPDDR5X for the energy efficiency and cost (lower
         | is better), whereas NVIDIA will always prefer GDDR and HBM for
         | performance and cost (higher is better).
        
           | _zoltan_ wrote:
           | the GH/GB compute has LPDDR5X - a single or dual GPU shares
           | 480GB, depending if it's GH or GB, in addition to the HBM
           | memory, with NVLink C2C - it's not bad!
        
             | wtallis wrote:
             | Essentially, the Grace CPU is a memory and IO expander that
             | happens to have a bunch of ARM CPU cores filling in the
             | interior of the die, while the perimeter is all PHYs for
             | LPDDR5 and NVLink and PCIe.
        
               | _zoltan_ wrote:
               | fully agree!
               | 
               | with MGX and CX8 we see PCIe root moving to the NIC,
               | which is very exciting.
        
               | rbanffy wrote:
               | > have a bunch of ARM CPU cores filling in the interior
               | of the die
               | 
               | The main OS needs to run somewhere. At least for now.
        
         | 3abiton wrote:
         | What's the math on the $50k nvidia cluster? My understanding
         | these things cost ~$8k and you can at least get 5 for $40k,
         | that's around half a tb.
         | 
         | That being said, for inference mac still remain the best, and
         | the M5 Ultra will even be a better value with its better PP.
        
           | reilly3000 wrote:
           | GPUs: 4x NVIDIA RTX 6000 Blackwell (96GB VRAM each) * Cost: 4
           | x $9,000 = $36,000
           | 
           | * CPU: AMD Ryzen Threadripper PRO 7995WX (96-Core) * Cost:
           | $10,000
           | 
           | * Motherboard: WRX90 Chipset (supports 7x PCIe Gen5 slots) *
           | Cost: $1,200
           | 
           | * RAM: 512GB DDR5 ECC Registered * Cost: $2,000
           | 
           | * Chassis & Power: Supermicro or specialized Workstation case
           | + 2x 1600W PSUs. * Cost: $1,500
           | 
           | * Total Cost: ~$50,700
           | 
           | It's a bit maximalist, but if you had to spend $50k it's
           | going to be about as fast as you can make it.
        
             | broretore wrote:
             | This is basically a tinybox pro?
        
         | yieldcrv wrote:
         | 15 t/s way too slow for anything but chatting, call and
         | response, and you don't need a 3T parameter model for that
         | 
         | Wake me up when the situation improves
        
           | rbanffy wrote:
           | Just wait for the M5-Ultra with a terabyte of RAM.
        
         | dsrtslnd23 wrote:
         | what about a GB300 workstation with 784GB unified mem?
        
           | wmf wrote:
           | $95K
        
             | rbanffy wrote:
             | I miss the time you could go to Apple's website and build
             | the most obscene computer possible. With the M series, all
             | options got a lot more limited. IIRC, an x86 Mac Pro with
             | 1.5 TB of RAM, a big GPU and the two accelerators would
             | yield an eye watering hardware bill.
             | 
             | Now you need to add 8 $5K monitors to get something
             | similarly ludicrous.
        
           | rbanffy wrote:
           | That thing will be extremely expensive I guess. And neither
           | CPU nor GPU have that much memory. It's also not a great
           | workstation either - macOS is a lot more comfortable to use.
        
       | ComputerGuru wrote:
       | Imagine if the Xserve was never killed off. Discontinued 14 years
       | ago, now!
        
         | icedchai wrote:
         | If it was still around, it would probably still be stuck on M2,
         | just like the Mac Pro.
        
       | stego-tech wrote:
       | This doesn't remotely surprise me, and I can guess Apple's AI
       | endgame:
       | 
       | * They already cleared the first hurdle to adoption by shoving
       | inference accelerators into their chip designs by default. It's
       | why Apple is so far ahead of their peers in local device AI
       | compute, and will be for some time.
       | 
       | * I suspect this introduction isn't just for large clusters, but
       | also a testing ground of sorts to see where the bottlenecks lie
       | for distributed inference in practice.
       | 
       | * Depending on the telemetry they get back from OSes using this
       | feature, my suspicion is they'll deploy some form of distributed
       | local AI inference system that leverages their devices tied to a
       | given iCloud account or on the LAN to perform inference against
       | larger models, but without bogging down any individual device (or
       | at least the primary device in use)
       | 
       | For the endgame, I'm picturing a dynamically sharded model across
       | local devices that shifts how much of the model is loaded on any
       | given device depending on utilization, essentially creating
       | local-only inferencing for privacy and security of their end
       | users. Throw the same engines into, say, HomePods or AppleTVs, or
       | even a local AI box, and voila, you're golden.
       | 
       | EDIT: If you're thinking, "but big models need the higher latency
       | of Thunderbolt" or "you can't do that over Wi-Fi for such huge
       | models", you're thinking too narrowly. Think about the devices
       | Apple consumers own, their interconnectedness, and the
       | underutilized but standardized hardware within them with
       | predictable OSes. Suddenly you're not jamming existing models
       | onto substandard hardware or networks, but rethinking how to run
       | models effectively over consumer distributed compute. Different
       | set of problems.
        
         | threecheese wrote:
         | I think you are spot on, and this fits perfectly within my
         | mental model of HomeKit; tasks are distributed to various
         | devices within the network based on capabilities and
         | authentication, and given a very fast bus Apple can scale the
         | heck out of this.
        
           | stego-tech wrote:
           | Consumers generally have far more compute than they think;
           | it's just all distributed across devices and hard to utilize
           | effectively over unreliable interfaces (e.g. Wi-Fi). If Apple
           | (or anyone, really) could figure out a way to utilize that at
           | modern scales, I wager privacy-conscious consumers would
           | gladly trade some latency in responses in favor of superior
           | overall model performance - heck, branding it as "deep
           | thinking" might even pull more customers in via marketing
           | alone ("thinks longer, for better results" or some vaguely-
           | not-suable marketing slogan). It could even be made into an
           | API for things like batch image or video rendering, but
           | without the hassle of setting up an app-specific render farm.
           | 
           | There's definitely something there, but Apple's really the
           | only player setup to capitalize on it via their halo effect
           | with devices and operating systems. Everyone else is too
           | fragmented to make it happen.
        
         | fwip wrote:
         | The bandwidth of rdma over thunderbolt is so much faster (and
         | lower latency) than Apple's system of mostly-wireless devices,
         | I can't see how any learnings here would transfer.
        
           | stego-tech wrote:
           | You're thinking, "You can't put modern models on that sort of
           | distributed compute network", which is technically correct.
           | 
           | I was thinking, "How could we package or run these _kinds_ of
           | large models or workloads across a consumer 's distributed
           | compute?" The Engineer in me got as far as "Enumerate devices
           | on network via mDNS or Bonjour, compare keys against iCloud
           | device keys or otherwise perform authentication, share
           | utilization telemetry and permit workload scheduling/balance"
           | before I realized that's probably what they're testing here
           | to a degree, even if they're using RDMA.
        
         | wmf wrote:
         | _inference accelerators ... It's why Apple is so far ahead of
         | their peers in local device AI compute, and will be for some
         | time._
         | 
         | Not really. llama.cpp was just using the GPU when it took off.
         | Apple's advantage is more VRAM capacity.
         | 
         |  _this introduction isn't just for large clusters_
         | 
         | It doesn't work for large clusters at all; it's limited to 6-7
         | Macs and most people will probably use just 2 Macs.
        
       | 650REDHAIR wrote:
       | Do we think TB4 is on the table or is there a technical
       | limitation?
        
       | piskov wrote:
       | George Hotz made nvidia running on macs with his tinygrad via
       | usb4
       | 
       | https://x.com/__tinygrad__/status/1980082660920918045
        
         | throawayonthe wrote:
         | https://social.treehouse.systems/@janne/115509948515319437
         | nvidia on a 2023 Mac Pro running linux :p
        
           | piskov wrote:
           | Geohotz stuff anyone can run today
        
       | londons_explore wrote:
       | Nobodies gonna take them seriously till they make something rack
       | mounted and that isn't made of titanium with pentalobe screws...
        
         | moralestapia wrote:
         | You might ignore this but, for a while, Mac Mini clusters were
         | a thing and they were capex and opex effective. That same setup
         | is kind of making a comeback.
        
           | londons_explore wrote:
           | It's in a similar vein to the PS2 linux cluster or someone
           | trying to use vape CPU's as web servers...
           | 
           | It might be cost effective, but the supplier is still saying
           | "you get no support, and in fact we might even put roadblocks
           | in your way because you aren't the target customer".
        
             | moralestapia wrote:
             | True.
             | 
             | I'm sure Apple could make a killing on the server side,
             | unfortunately their income from their other products is so
             | big that even if that's a 10B/year opportunity they'll be
             | like "yawn, yeah, whatever".
        
               | fennecbutt wrote:
               | Doubt. A 10B idea is still a promotion. And if capitalism
               | is shrinkflationing hard, which it is atm, then
               | capitalists would not leave something like that on the
               | table.
        
           | fennecbutt wrote:
           | They were only a thing to do ci/compilation related to apples
           | os because their walled garden locked using other platforms
           | out. You're building an iPhone or mac app? Well your ci needs
           | to be on a cluster of apple machines.
        
       | cluckindan wrote:
       | This sounds like a plug'n'play physical attack vector.
        
         | guiand wrote:
         | For security, the feature requires setting a special option
         | with the recovery mode command line:
         | 
         | rdma_ctl enable
        
       | int32_64 wrote:
       | Apple should setup their own giant cloud of M chips with tons of
       | vram, make Metal as good as possible for AI purposes, then market
       | the cloud as allowing self-hosted models for companies and
       | individuals that care about privacy. They would clean up in all
       | kinds of sectors whose data can't touch the big LLM companies.
        
         | wmf wrote:
         | That exists but it's only for iUsers running Apple models.
         | https://security.apple.com/blog/private-cloud-compute/
        
         | make3 wrote:
         | The advantages of having a single big memory per gpu are not as
         | big in a data center where you can just shard things between
         | machines and use the very fast interconnect, saturating the
         | much faster compute cores of a non Apple GPU from Nvidia or AMD
        
       | sebnukem2 wrote:
       | I didn't know they skipped 10 version numbers.
        
         | badc0ffee wrote:
         | They switched to using the year.
        
       | thatwasunusual wrote:
       | Can someone do an ELI5, and why this is important?
        
         | wmf wrote:
         | It's faster and lower latency than standard Thunderbolt
         | networking. Low latency makes AI clusters faster.
        
       | schmuckonwheels wrote:
       | That's nice but
       | 
       | Liquid (gl)ass still sucks.
        
       | yalogin wrote:
       | As someone that is not familiar with rdma, dos it mean I can
       | connect multiple Macs and run inference? If so it's great!
        
         | wmf wrote:
         | You've been able to run inference on multiple Macs for around a
         | year but now it's much faster.
        
       | 0manrho wrote:
       | Just for reference:
       | 
       | Thunderbolt5's stated "80Gbps" bandwidth comes with some caveats.
       | That's the figure for either Display Port bandwidth itself or in
       | practice more often realized by combining the data channel
       | (PCIe4x4 ~=64Gbps) with the display channels (=<80Gbps if used in
       | concert with data channels), and potentially it can also do
       | unidirectional 120Gbps of data for some display output scenarios.
       | 
       | If Apple's silicon follows spec, then that means you're most
       | likely limited to PCIe4x4 ~=64Gbps bandwidth per TB port, with a
       | slight latency hit due to the controller. That Latency hit is
       | ItDepends(TM), but if not using any other IO on that
       | controller/cable (such as display port), it's likely to be less
       | than 15% overhead vs Native on average, but depending on drivers,
       | firmware, configuration, usecase, cable length, and how apple
       | implemented TB5, etc, exact figures very. And just like how 60FPS
       | Average doesn't mean every frame is exactly 1/60th of a second
       | long, it's entirely possible that individual packets or niche
       | scenarios could see significantly more latency/overhead.
       | 
       | As a point of reference Nvidia RTX Pro (formerly known as quadro)
       | workstation cards of Ada generation and older along with most
       | modern consumer grahics cards are PCIe4 (or less, depending on
       | how old we're talking), and the new RTX Pro Blackwell cards are
       | PCIe5. Though comparing a Mac Studio M4 Max for example to an
       | Nvidia GPU is akin to comparing Apples to Green Oranges
       | 
       | However, I mention the GPU's not just to recognize the 800lb AI
       | compute gorilla in the room, but also that while it's possible to
       | pool a pair of 24GB VRAM GPU's to achieve a 48GB VRAM pool
       | between them (be it through a shared PCIe bus or over NVlink),
       | the performance does not scale linearly due to PCIe/NVLinks
       | limitations, to say nothing of the software, and configuration
       | and optimization side of things also being a challenge to
       | realizing max throughput in practice.
       | 
       | This is also just as true as a pair of TB5 equipped macs with
       | 128GB of memory each using TB5 to achieve a 256GB Pool will take
       | a substantial performance hit compared to on otherwise equivalent
       | mac with 256GB. (capacities chosen are arbitrary to illustrate
       | the point). The exact penalty really depends on usecase and how
       | sensitive it is to the latency overhead of using TB5 as well as
       | the bandwidth limitation.
       | 
       | It's also worth noting that it's not just entirely possible with
       | RDMA solutions (no matter the specifics) to see worse performance
       | than using a singular machine if you haven't properly optimized
       | and configured things. This is not hating on the technology, but
       | a warning from experience for people who may have never dabbled
       | to not expect things to just "2x" or even just better than 1x
       | performance just by simply stringing a cable between two devices.
       | 
       | All that said, glad to see this from Apple. Long overdue in my
       | opinion as I doubt we'll see them implement an optical network
       | port with anywhere near that bandwidth or RoCEv2 support, much
       | less a expose a native (not via TB) PCIe port on anything that's
       | a non-pro model.
       | 
       | EDIT: Note, many mac skus have multiple TB5 ports, but it's
       | unclear to me what the underlying architecture/topology is there
       | and thus can't speculate on what kind of overhead or total
       | capacity any given device supports by attempting to use multiple
       | TB links for more bandwidth/parallelism. If anyone's got an SoC
       | diagram or similar refernce data that actually tells us how the
       | TB controller(s) are uplinked to the rest of the SoC, I could go
       | in more depth there. I'm not an Apple silicon/MacOS expert. I do
       | however have lots of experience with RDMA/RoCE/IB clusters,
       | NVMeoF deployments, SXM/NVlink'd devices and generally
       | engineering low latency/high performance network fabrics for
       | distributed compute and storage (primarily on the
       | infrastructure/hardware/ops side than on the software side) so
       | this is my general wheelhouse, but Apple has been a relatively
       | blindspot for me due to their ecosystem generally lacking
       | features/support for things like this.
        
       | kjkjadksj wrote:
       | Remember when they enabled egpu over thunderbolt and no one cared
       | because the thunderbolt housing cost almost as much as your
       | macbook outright? Yeah. Thunderbolt is a racket. It's a god
       | damned cord. Why is it $50.
        
         | wmf wrote:
         | In this case Thunderbolt is much much cheaper than 100G
         | Ethernet.
         | 
         | (The cord is $50 because it contains two active chips BTW.)
        
           | geerlingguy wrote:
           | Yeah, even decent 40 Gbps QSFP+ DAC cables are usually $30+,
           | and those don't have active electronics in them like
           | Thunderbolt does.
           | 
           | The ability to also deliver 240W (IIRC?) over the same cable
           | is also a bit different here, it's more like FireWire than a
           | standard networking cable.
        
       | FridgeSeal wrote:
       | That's great for AI people, but can we use this for other
       | distributed workloads that aren't ML?
        
         | geerlingguy wrote:
         | I've been testing HPL and mpirun a little, not yet with this
         | new RDMA capability (it seems like Ring is currently the
         | supported method)... but it was a little rough around the
         | edges.
         | 
         | See: https://ml-
         | explore.github.io/mlx/build/html/usage/distribute...
        
         | dagmx wrote:
         | Sure, there's nothing about it that's tied to ML. It's faster
         | interconnect , use it for many kinds of shared compute
         | scenarios.
        
       | nickysielicki wrote:
       | This is such a weird project. Like where is this running at
       | scale? Where's the realistic plan to ever run this at scale?
       | What's the end goal here?
       | 
       | Don't get me wrong... It's super cool, but I fail to understand
       | why money is being spent on this.
        
         | aurareturn wrote:
         | The end goal is that Macs become good local LLM inference
         | machines and for AI devs to keep using Macs.
        
           | nickysielicki wrote:
           | The former will never happen and the latter is a certainty.
        
             | aurareturn wrote:
             | The former is already true and will become even more true
             | when M5 Pro/Max/Ultra release.
        
       | pjmlp wrote:
       | Maybe Apple should rethink bringing back Mac Pro desktops with
       | pluggable GPUs, like that one in the corner still playing with
       | its Intel and AMD toys, instead of a big box full of air and pro
       | audio cards only.
        
       | nottorp wrote:
       | It's good to sell shovels :)
        
       | zeristor wrote:
       | Will Apple be able to ramp up M3 Ultra MacStudios if this becomes
       | a big thing?
       | 
       | Is this part of Apple's plan of building out server side AI
       | support using their own hardware?
       | 
       | If so they would need more physical data centres.
       | 
       | I'm guessing they too would be constrained by RAM.
        
       | irusensei wrote:
       | I am waiting for M5 studio but due to current price of hardware
       | I'm not sure it will be at a level that I would call affordable.
       | Currently I'm watching for news and if there is any announcement
       | prices will go up I'll probably settle for an M4 Max.
        
       | DesiLurker wrote:
       | does this means an egpu might finally work with macbook-pro or
       | studio?
        
         | wmf wrote:
         | No.
        
       | jamesfmilne wrote:
       | Anyone found any APIs related to this?
       | 
       | I'd have some other uses for RDMA between Macs.
        
         | jamesfmilne wrote:
         | I found some useful clues here. Looks like it uses the regular
         | InfiniBand RDMA APIs.
         | 
         | https://github.com/Anemll/mlx-rdma/commit/a901dbd3f9eeefc628...
        
       | TheRealPomax wrote:
       | IS this... good? Why is this something that the underlying OS
       | itself should be involved in at all?
        
         | wmf wrote:
         | Networking is part of the OS's job.
        
       ___________________________________________________________________
       (page generated 2025-12-13 23:01 UTC)