[HN Gopher] Ensu - Ente's Local LLM app
___________________________________________________________________
Ensu - Ente's Local LLM app
Author : matthiaswh
Score : 316 points
Date : 2026-03-25 12:49 UTC (10 hours ago)
(HTM) web link (ente.com)
(TXT) w3m dump (ente.com)
| moqster wrote:
| Heard the first time about them (ente) yesterday in a discussion
| about "which 2FA are u using?". Directly switched to
| https://ente.com/auth/ on Android and Linux Desktop and very
| happy with it.
|
| Going to give this a try...
| _factor wrote:
| You presumably had a working 2fa app already, but off the cuff
| decide to switch to new unvetted variant X; basically unknown
| auth system after reading a few paragraphs of text in an
| afternoon?
|
| Does this seem sound?
| ahofmann wrote:
| While I would have the same reaction, in this case I think it
| is a sane decision. Ente is cornering the privacy market and
| I think they're doing a great job. They have a lot to lose
| (trust) and it would be stupid if they did something shady
| with the data entered in the 2FA app.
| stonogo wrote:
| > cornering the privacy market
|
| this seems self-contradictory
| ahofmann wrote:
| Sorry, English is not my first language and I tried to
| look clever.
| PurpleRamen wrote:
| Not knowing them, how could OP trust them instantly?
| Whether they really have that trust or not, you have to
| know them for a while and from many different trustable
| sources. The story is a bit strange.
| dotancohen wrote:
| There are the issues of competence and track record, not
| only intent.
| yolo_420 wrote:
| Ente is extremely well known in the privacy circles, so this
| is not just some random company with a random app out of
| nowhere. Check PrivacyGuides for example.
| testdelacc1 wrote:
| Ok I checked privacyguides.
|
| Here's where it was added to PrivacyGuides - https://github
| .com/privacyguides/privacyguides.org/issues/36.... The
| person opening the issue is the CEO of ente. So the CEO of
| ente gets his company mentioned in PrivacyGuides back when
| it was new and that makes it more legit?
| yolo_420 wrote:
| PrivacyGuides goes through their own process of vetting
| (whether you would agree with their process or not that's
| another topic) so I think the discussion to add Ente
| Photos is the more relevant link
| https://discuss.privacyguides.net/t/ente-photo-
| management/11...
| zaphod12 wrote:
| if it helps, I've used ente for a year and I really like it.
| deltoidmaximus wrote:
| I ended up picking them because they were the only open
| source one that worked on all my devices IIRC.
|
| https://en.wikipedia.org/wiki/Comparison_of_OTP_applications
| utopiah wrote:
| What's the risk?
|
| They just store tokens, without other FA at "worst" you get
| locked of your account but nobody else has access either.
| You're also supposed to, as good practice, not be limited to
| token generation and typically have a dozen or so of recovery
| tokens. Also if they were somewhat not working at doing the 1
| task they should do, namely generate tokens, then you won't
| be able to use them so it won't even be added.
|
| So... I might be missing something, can you please explain
| what worries you and why I should thus worry too?
| testdelacc1 wrote:
| Not saying they're a paid promoter. But if I paid someone to
| speak about my newly launched product, they'd say something
| exactly like that. "Never heard of these guys before, but I
| loved their other product you've never heard of. I'm super
| excited to try this one!"
| mschulze wrote:
| Oh, wow, thanks for posting that. I switched to Ente for my
| photos recently, had no idea they also have a 2FA app. I was
| looking for a replacement for Aegis (after a switch to iOS),
| and this can even import from Aegis backup files. Neat. This
| means I can finally ditch my old phone I still had to have
| around just for 2FA :)
| glitchc wrote:
| This sounds like an ad.
| gwerbret wrote:
| As do most of the associated comments. I think we're
| surrounded by bots.
| mschulze wrote:
| I'm not a bot. Check my comment history and account age.
| yomismoaqui wrote:
| You sure were when you posted those comments, but now, we
| cannot be sure...
|
| So you look down you see a tortoise. It's crawling
| towards you.
| mschulze wrote:
| I mean I get it, astroturfing is a real problem and an
| annoying one for communities. But I also have no idea how
| to prove to you that I am neither a bot nor shilling
| here.
| vaporwario wrote:
| agreed. i have never seen anyone (let alone an assortment)
| of hacker news users saying "i switched my 2fa to this
| after seeing how great it was!" Not really sure how one
| 'switches their 2fa' to an LLM...
| mschulze wrote:
| This thread is about the 2FA app, not the LLM app. I
| don't care about the LLM app. What's this witch hunt?
| This app literally solved a (self-inflicted) problem I
| was having for some years now where I was keeping an old
| phone around just for MFA. I even thought about creating
| an iOS app that's compatible with Aegis files (actually I
| even _started_ working on that, but didn't get far) just
| to solve my problem. Now I don't have to, thanks to a
| comment here, and that's why I posted. Geez. I guess I'll
| stay with negative comments for the future, they seem to
| be more trustworthy.
| NewsaHackO wrote:
| Yea, everything about this post is just weird. IDK if they
| are even bots vs paid actors vs actual people who are
| clueless etc.
| testdelacc1 wrote:
| For sure. Getting shady vibes from ente. I'll be avoiding
| them.
| Fervicus wrote:
| I am not a bot and I am not associated with this company in
| any way. But I am a happy user of Ente Auth as well. This AI
| thing they made however just gives off "we have to do
| something with AI or we'll be left behind" vibes.
| dmboyd wrote:
| I was just thinking their end goal seems to be to harvest creds
| by putting their own rebadged distribution of local models.
| That's the only "business" model that makes sense.
|
| Expressly harvesting creds through a 2FA app seems a little
| more direct.
| sylens wrote:
| Ente offers E2EE photo hosting, the storage they sell through
| subscriptions to that is their business model. Their main
| selling point is that all machine learning to cluster faces
| is done on your devices. I would assume that they want more
| users to train their models on to improve their core offering
| dotancohen wrote:
| I'm very happy syncing between KeepassXC on Debian and
| Keepass2Android on mobile. It handles TOTP accoss devices.
|
| What I'm missing is a way to create and use Passkeys across
| devices. My use case does not support creating a new Passkey on
| every device, I need to sync them via servers I control. The
| system that supports that will be the system that I migrate to.
| moontear wrote:
| And you can self-host the server if you want to! Running Ente
| Auth since quite a while now and am very happy with it.
| VladVladikoff wrote:
| Maybe I'm missing it but the page is really light on technical
| information. Is this a quantized / distilled model of a larger
| LLM? Which one? How many parameters? What quantization? What T/s
| can I expect? What are the VRAM requirements? Etc etc
| hellcow wrote:
| I tried it on my iPhone 13 mini. I believe the model you get
| changes depending on your phone specs. For me it downloaded a
| ~1.3GB model which can speak in complete sentences but can't do
| much beyond that. Can't blame them though--that model is tiny,
| and my device wasn't designed for this.
| NitpickLawyer wrote:
| You can see what it uses here - https://github.com/ente-
| io/ente/blob/main/web/apps/ensu/src/...
|
| Either LFM2.5-1.6B-4bit or Qwen3.5-2B-8bit or Qwen3.5-4B-4bit
| embedding-shape wrote:
| Huh, 1.6B/2B/4B models, I guess they weren't joking when they
| said "not as powerful as ChatGPT or Claude Code". Also unsure
| why they said "Claude Code", it's not an CLI agent AFAIK?
| dgb23 wrote:
| This seems to be a general chat app, but otherwise small
| models can be very effective within the right use cases and
| orchestration.
| embedding-shape wrote:
| > otherwise small models can be very effective within the
| right use cases and orchestration
|
| _very_ limited amount of use cases, perhaps. As a
| generalized chat assistant? I 'm not sure you'd be able
| to get anything of value out from them, but happy to be
| proven otherwise. I have all of those locally already,
| without fine-tuning, what use case could I try right now
| where any of those are "very effective"?
| dgb23 wrote:
| Judging from my experimentation with local models:
|
| You can use a small coding model to produce working code
| with a deterministic workflow (ex: state machine) if you
| carefully prune the context and filter down what it can
| do per iteration. Instead of letting it "reason" through
| an ever growing history, you give it distinct piecemeal
| steps with tailored context.
|
| I think this can be generalized to:
|
| Anything that can be built from small, well understood
| pieces and can be validated and fixed step by step. Then
| the challenge becomes designing these workflows and
| automating them.
|
| (I'm not there yet, but one thing I have in mind might be
| a hybrid approach where the planning is produced by a
| more expensive model. The output it has to produce are
| data driven state machines or behavior trees (so they can
| be validated deterministically). Then it offloads the
| grunt work to a small, local model. When it's done, the
| work gets checked etc.)
| Mashimo wrote:
| > Also unsure why they said "Claude Code", it's not an CLI
| agent AFAIK?
|
| Claude Code is a Desktop app as well.
| yomismoaqui wrote:
| The consfusing way AI companies like to name products is
| something to be studied.
| lancekey wrote:
| I don't think so. IIRC the desktop app is called Claude
| and it has a code option in the UI.
| Mashimo wrote:
| If you go to the product website:
| https://claude.com/product/claude-code
|
| > Use Claude Code where you work
|
| > Desktop Termianl IDE WEb and iOS Slack
|
| Not that it is important any way -\\_(tsu)_/-
| embedding-shape wrote:
| Ok, but "Claude Code"/"Claude Desktop" regardless is
| software, a tool, not a model/LLM. Doesn't make much
| sense as they've written it.
| Mashimo wrote:
| For the end user who just installs the app it's probably
| all the same. It's not a technical document.
|
| For the user it's just important that the small grimlin
| that sits in the Ente app is not as smart as the grimlin
| that sits in the Claude app.
| dr_kiszonka wrote:
| I so wanted to love Liquid AI's models, but despite their
| speed I was never able to get anything useful out of them.
| Even their larger models can't be trusted with simple stuff
| like inserting a column into a markdown table. The
| advertised tool calling is also not great. What I found
| interesting was that the ones I tried were a little light
| on guardrails.
|
| I would really like to know what people use these small and
| tiny models for. If any high-karma users are reading it,
| would you consider posting Ask HN?
| sync wrote:
| Hmm, the Mac app downloaded gemma-3-4b-it-Q4_K_M.gguf for me
| (on an Apple M4) - maybe the desktop apps download different
| models?
|
| Though, I don't see any references to Gemma at all in the
| open source code...
| woadwarrior01 wrote:
| The only takeaway for me from this is that the Ente is at <
| $10m/year in revenue. Because the LFM model license has a
| commercial use threshold of $10m.
|
| https://www.liquid.ai/lfm-license
| ahofmann wrote:
| I have the same questions. After installing the app, it
| downloads 2.5 GB of data. I presume this is the model.
| juliushuijnk wrote:
| I'm working on a rather simple idea; a Wordpress plugin that
| allows you to use a local LLM inside your wordpress CMS.
|
| It requires a Firefox add-on to act as a bridge:
| https://addons.mozilla.org/en-US/firefox/addon/ai-s-that-hel...
|
| There is honestly not much to test just yet, but feel free to
| check it out here, provide feedback on the idea:
| https://codeberg.org/Helpalot/ais-that-helpalot
|
| The essence works, I was able to let it make a simple summary on
| CMS content. So next is making it do something useful, and making
| it clear how other plugins could use it.
| HelloUsername wrote:
| Spam? Ad?
|
| Also: "Your AI agent can now create, edit, and manage content
| on WordPress.com" https://wordpress.com/blog/2026/03/20/ai-
| agent-manage-conten...
| juliushuijnk wrote:
| Spam for what? This is hackernews, I'm "hacking something" to
| push more control to users.
|
| I'm talking about connecting Ollama to your wordpress.
|
| Not via MCP or something that's complicated for a relatively
| normal user. But thanks for the link.
| juliushuijnk wrote:
| It seems your link about the Wordpress variation validated
| my idea :).
|
| If the new Wordpress feature would allow for connecting to
| Ollama, then there is no need anymore for my plugin. But I
| don't see that in the current documentation.
|
| So for now, I see my solution being superior for anyone who
| doesn't have a paid subscription, but has a decent laptop,
| that would like to use an LLM 'for free' (apart from power
| usage) with 100% privacy on their website.
| bilekas wrote:
| > use a local LLM inside your wordpress CMS
|
| For when wordpress doesn't have enough exploits and bugs as it
| is. Also why bother with wordpress in the first place if you're
| already having an LLM spit out content for you ?
| juliushuijnk wrote:
| What's your point? Don't use LLM for CMS content? That my
| code is buggy? Or that people shouldn't trust the LLM they
| run on their computer on their own website?
|
| You can check the code for exploits yourself. And other than
| that it's just your LLM talking to your own website.
|
| > Also why bother with wordpress in the first place
|
| Weird question, but sure, I use WordPress, because I have a
| website that I want to run with a simple CMS that can also
| run my custom Wordpress plugins.
| chocks wrote:
| This looks amazing! As I learn and experiment more with local
| LLMs, I'm becoming more of a fan of local/offline LLMs. I believe
| there's a huge gap between local LLM based apps and commercial
| models like Claude/ChatGPT. Excited to see more apps leveraging
| local LLMs.
| netfl0 wrote:
| Weird hype going on here in comments.
| kylehotchkiss wrote:
| Also weird arrogance. Yeah, somebody else could have vibe coded
| it in a week. But they didn't, so they don't get the 100 HN
| klout points for it.
|
| Helping non-technical people get off of ChatGPT.com and using
| increasingly better local models seems worth celebrating and
| continued iteration.
| nathan_compton wrote:
| Please god stop letting LLMs write your copy. My brain just
| slides right over this slop. Perhaps you have a useful product
| but christ almighty I cannot countenance this boring machine
| generated text.
| franze wrote:
| if you are into local LLMs check out apfel
|
| https://github.com/Arthur-Ficial/apfel
|
| Apple Ai on the command line
| echion wrote:
| Looks excellent -- thanks; shame older intel macs don't get it
| (a lot of those still around)
| hmokiguess wrote:
| I've been having fun with this one https://github.com/osaurus-
| ai/osaurus
| koehr wrote:
| I just tried it. It downloaded Qwen3.5 2B on my phone and it's
| pretty coherent in its sentences, but really annoying with the
| amount of Ente products mentioned in every occasion. Other than
| that it's fast enough to talk to and definitely an easy way to
| run a model locally on your phone.
| sunaookami wrote:
| >but really annoying with the amount of Ente products mentioned
| in every occasion
|
| https://github.com/ente-io/ente/blob/f254af939ff6950b63edf5f...
| Here is the system prompt, kinda embarassing
| giuscri wrote:
| what's embarrassing about that?
| mkagenius wrote:
| Had used cactus before -
| https://news.ycombinator.com/item?id=44524544
|
| Then moved to pocket pal now for local llm.
| dgb23 wrote:
| The (hn) title is misleading (unlike the actual title): It's an
| LLM _App_ not an LLM.
| post-it wrote:
| > This is not the beginning, nor is this the end. This is just a
| checkpoint.
|
| Come onnnnnn. I would rather read a one line "Check out our
| offline llm" rather than a whole press release of slop.
|
| This looks very neat. I'm not familiar with the nitty gritty of
| AI so I really don't understand how it can reply so quickly
| running on an iPhone 16. But I'm not even going to bother
| searching for details because I don't want to read slop.
| maxloh wrote:
| There is also another app called Off Grid, which lets you run any
| model from Hugging Face (of course you need to choose one your
| phone can handle).
|
| https://github.com/alichherawalla/off-grid-mobile-ai
| talking_penguin wrote:
| How is this any different from Ollama plus Open Web UI?
| kennywinker wrote:
| None of that runs on an ios or android device.
| jubilanti wrote:
| There's dozens of local inference apps that basically wrap
| llama.cpp and someone else's GGUFs. The decentralized sync
| history part seems new? Not much else. But the advertisement copy
| is so insufferably annoying in how it presents this wrapper as a
| product.
|
| Have a comparison chart to Ollama, LMStudio, LocalAI, Exo,
| Jan.AI, GPT4ALL, PocketPal, etc.
| bee_rider wrote:
| There are so many wrappers that are obviously wrappers. I
| wonder if part of the value proposition here is that it is
| "like a product." I have no idea if they actually achieve that,
| though, and doubt it really could be proven on a site.
| gardnr wrote:
| oMLX is worth a look too if you are on a mac.
| cdrnsf wrote:
| I like Ente, but isn't their core product a photos application?
| Its offshoots like this and 2FA feel incongruous.
| alterom wrote:
| Their core product is _local ML inference_ in the context of a
| photo app, i.e. a _drop-in cloud dependency removal
| /replacement_ for non-technical, privacy-conscious users as
| well as those who want advanced functionality offline.
|
| This does the same for language models.
| cdrnsf wrote:
| I hadn't thought of it that way. Makes sense.
| FitchApps wrote:
| Have you tried WebLLM? Or this wrapper: CodexLocal.com Basically,
| you would have a rather simple but capable LLM right in your
| browser using WebLLM and GPU
| emehex wrote:
| There are literally 1000s of these types of apps. Why is this on
| the Front Page?
| alterom wrote:
| 1000s?
|
| I'd love to know a few more local LLM apps that are available
| on Android _and_ iOS _and_ Mac /PC under the same branding that
| I can point my non-technical friends to as a ChatGPT
| alternative that works offline (but still has sync across the
| devices).
|
| Could you recommend a few?
| lone-cloud wrote:
| Any half capable engineer can vibe code this in a week. Who
| cares?
| H8crilA wrote:
| Someone still has to.
| alterom wrote:
| _> Any half capable engineer can vibe code this in a week. Who
| cares?_
|
| The people who got tired of waiting for "any half capable
| engineer" to do so.
| imadch wrote:
| What do you mean by IA in your device ? is it a local LLM ? if
| yeas how much params 4B or 8B...?? device requirements not
| mentionned too
| kennywinker wrote:
| Looks like it checks your device specs and downloads whatever
| the best model that will work? On mine it's using a 3.5b
| version of llama
| jasongill wrote:
| I love Ente Auth, but Ente (as a company/organization) does a
| somewhat poor job of calling out their non-photos apps in their
| branding and on their website. If you go to the "Download" button
| at the top of the page on this page about their LLM chat app, it
| downloads... their photo sharing application. If you click Sign
| Up, it takes you to a signup page with the browser title "Ente
| Photos" but the page text says "Private backups for your
| memories" with a picture of a lock - is that the Ente Auth
| signup, or the Ente Photos app signup?
|
| A little bit of cleanup on their site to break out "Ente, our
| original photo sharing app" from the rest of their apps would do
| wonders, because I had to search around on the announcement to
| find the download for this app, which feels about like trying to
| find the popular Ente Auth app on their website
| cromka wrote:
| This is one of the reason I, as their user, am moving away.
| Things feel half-baked and I stopped trusting it with my data.
| I self host and the details for this were all over the place.
| Some of my contributions cleaning up the docs were rejected, so
| I grew even more wary. I am moving to Immich, even though I'd
| prefer e2ee for my photos even if I self host them.
|
| EDIT: and there are long-standing bugs like this one,
| unaddressed: https://github.com/ente-io/ente/issues/3087
| jasongill wrote:
| Further proving my point, I wasn't sure if you - a fellow
| commenter! - were talking about Ente Auth or Ente Photos
| until I re-read your comment and the linked issue. I think
| that they have great product(s) but terrible branding and
| apparently some growing pains as well.
| kelvinjps10 wrote:
| Well ente photos is the one that provides the funding
| tim-projects wrote:
| This app isn't very useful but it did get me thinking.
|
| I have a phone in a drawer I could install termux and ollama on
| over tailscale and then I'd have an always on llm for super light
| tasks.
|
| I do really long for a private chat bot but I simply don't have
| access to the hardware required. Sadly I think it's going to be
| years to get there..
| QubridAI wrote:
| This is the most important part of local AI maturing not just
| better models, but better productization of on-device inference
| for normal people.
| FusionX wrote:
| Given how the blog is presented, I assumed this was something
| novel that solved a unique problem, maybe a local multi-modal
| assistant for your device.
|
| I installed it and it's none of that. It is a mere wrapper around
| small local LLM models. And, it's not even multi-modal! Anyone
| could've one-shotted this in Claude in an hour (I'm not
| exaggerating).
|
| What's the target audience here? Your average person doesn't care
| about the privacy value proposition (at least not by severely
| sacrificing chat model's quality). And users who do want that
| control can already install LMStudio/Llama.cpp (which is dead
| simple to setup).
|
| The actual release product should've been what's described in
| "What's next" section.
|
| > Instead of general chat, we shape Ensu to have a more
| specialized interface, say like a single, never-ending note you
| keep writing on, while the LLM offers suggestions, critiques,
| reminders, context, alternatives, viewpoints, quotes. A second
| brain, if you will.
|
| > A more utilitarian take, say like an Android Launcher, where
| the LLM is an implementation detail behind an existing
| interaction that people are already used to.
|
| > Your agent, running on your phone. No setup, no management, no
| manual backups. An LLM that grows with you, remembers you, your
| choices, manages your tasks, and has long-term memory and
| personality.
| jubilanti wrote:
| > Anyone could've one-shotted this in Claude in an hour (I'm
| not exaggerating).
|
| This probably could have been one-shotted with Sonnet, not even
| Opus. Given how over indexed they are on LLM coding, Haiku
| might even be able to do it.
|
| This is actually an interesting coding model benchmark task now
| that I think about it.
| cyanydeez wrote:
| You'd think any one of these great LLMs that claim coding is
| over would take a non-trivial app and just clone it while
| fully documenting the process.
|
| If it's so great, why is there so little viscera documenting
| it's greatness? Just lots and lots of words.
| girvo wrote:
| They've done that for some tech, and the output has been...
| well, kind of impressive that it works at all, but bad in
| other ways (a GCC clone, SQLite re-impl, among others)
|
| Coding is definitely not over IMO. Not yet anyway
| chatmasta wrote:
| Is "this could have been one-shotted with Sonnet" the new "I
| could build this in a weekend?"
| post-it wrote:
| > Anyone could've one-shotted this in Claude in an hour
|
| I think they did. If you start the download and then open the
| sidebar and/or background the app, the download progress bar
| disappears and is replaced by the download button. If you press
| the download button again, the progress bar reappears at the
| correct point.
|
| I find that Claude often makes little statefulness mistakes
| like that. Human developers do too, but the slower and more
| iterative nature of human development makes it more likely that
| that would get caught.
| reactordev wrote:
| It's a platform play so they can get people onto their defunct
| photos platform. "Big Tech" in a little suit.
| Barbing wrote:
| All about immich now right?
| buster wrote:
| What do you when you say defunct photos platform?
| fauigerzigerk wrote:
| How is Ente Photos defunct? It's getting new features all the
| time and it works extremely well for me.
| i80and wrote:
| Defunct? I just switched to it a couple months ago, and it
| seems actively developed.
|
| (Though I think this announcement is sufficiently unpleasant
| I'm starting to reconsider)
| PhilipRoman wrote:
| Ente has a killer feature of supporting actual end-to-end
| encryption for photos. That alone puts them above many other
| competitors.
| kylehotchkiss wrote:
| Local LLM options for less technical people is worth
| celebrating IMO. No, not "anybody" can have one-shotted this in
| CC in an hour.
|
| We have not seen a tidal wave of untechnical people vibe coding
| up their own software solutions.
| collabs wrote:
| To add to this, the value that ente or someone like that can
| bring to the table here is a firm pledge to improve it and
| maintain it going forward.
|
| That to me is more valuable than code vibe coded by Claude in
| one afternoon.
| jermaustin1 wrote:
| > We have not seen a tidal wave of untechnical people vibe
| coding up their own software solutions.
|
| When my little brother who is a drummer, and has never even
| looked at "code" before, had claude on-shot a python app that
| let him download songs on youtube, extract the stems, collect
| tempo/key/etc information, then feed that into his DAW, all
| without ever looking at code, knowing what any of it did,
| etc., I knew that we were about to see a LOT of single-use
| applications.
|
| I'm not against it, honestly. I have always written little
| one-off scripts and apps that accomplished something faster
| than manually, now that those one-shots are possible with an
| LLM in seconds sometimes, it makes all my personal scripts so
| much easier... that said, I definitely read the scripts that
| are output, and attempt to step through them in a debugger
| before assuming it is all good.
| nozzlegear wrote:
| edit: nevermind I misread a word and made a social faux pas
|
| I do agree that more local LLM options are always better.
| Barbing wrote:
| >not
| nozzlegear wrote:
| Ope
| Barbing wrote:
| naux pas :)
| ttul wrote:
| I hate to say it, but this looks like the sort of thing a CEO
| told their team to build on Monday morning in a panic because
| they are grasping for ways to participate in the AI craze. And
| the team did just that: they built it that morning using Claude
| Code.
|
| There is truly nothing original here and the product doesn't
| have a chance in hell of earning money. Local LLMs on-device
| will be dominated by the device vendors, whose control of the
| hardware stack combined with their ability to subsidize
| billions of dollars of machine learning research gives them an
| unfair advantage. Apple knows what the next generation of
| silicon will deliver, and their ML engineers are already hard
| at work building models that will be highly optimized for that
| silicon a year or two ahead of time. Open source models are
| really great and are backed by well funded labs; however,
| delivering these models on-device in a way that pleases users
| will never be easier than it is for the vendors of the devices.
|
| Plus, device vendors have ways of making money from local LLMs
| that third-party app providers do not. They can make their
| local LLM free and earn money on the hardware play, without
| skipping a beat on the billions of dollars of ongoing R&D. I
| don't see how third party app vendors make money here when they
| will be competing with the decent, totally free alternative
| that Apple and Google (and Samsung etc.) will load on in the
| next year or two.
| Barbing wrote:
| Wanted to share a message here with the CEO not to feel too
| bad because little is more common than getting caught by this
| tech
|
| But where are they! https://ente.com/about
|
| Small team, rooting for them
| ttul wrote:
| I write my comment with admiration for founders, because I
| am one. That being said, chasing trends without paying
| attention to the steamroller has killed more than one very
| good company and I have plenty of scar tissue as
| evidence...
| usrusr wrote:
| Counter position (not sure it's better than yours): what are
| the chances that device makers would actually offer seriously
| local, and not just something that does work in airplane
| mode, but then still connects to their cloud later, if not
| for post-sale monetization then at least for features
| providing better brand lock-in? I mean just look at how well
| the market for TV sets that don't try to shove "services"
| down buyers' throats is developing...
|
| But sure, making money with standalone "local first is our
| headline feature" will be incredibly hard against those, no
| doubt about that. In light of the limited quality of what
| local models can achieve, the privacy bonus just won't compel
| many to pay. But that only means that this "morning with
| Claude" you are suggesting might be just the right amount of
| investment for the result you'd realistically expect. But is
| that so bad? I'd argue the reverse: bundling up the low
| hanging fruit but not by some hobbyist who will lose interest
| two weeks on but by a company big enough the keep it going
| while small enough to not be a VC furnace that will
| inevitably turn on users once the runway runs out (*), that's
| an opportunity to fill a niche few others can. Valuable for
| users who don't want to roll their own deployment of open
| source models (can't, or unwilling to commit to keeping them
| up to date, assuming that Ente does keep that ball rolling),
| and also valuable for the company of the investment actually
| is so low that it pays by raising awareness for their other
| products that apparently do earn them money.
|
| (*) I was googling around a little wondering if they actually
| are as close to bootstrapped as they seem on the surface, and
| yes, that's supposedly the core idea [0], but despite that
| they also took 100 kUSD in "non-diluting" (basically a gift
| then?) from Mozilla with the explicit goal "to promote
| independent AI and machine learning" [1]. So not a CEO whim
| but following up to a promise made earlier. If they actually
| did avoid spending all that money on a one-off but went
| smaller planning to keep it current for a longer time
| horizon, I'd congratulate them on an excellent choice.
|
| [0] https://ente.com/blog/5-years-of-ente/
|
| [1] https://ente.io/blog/mozilla-builders/
|
| The hn discussion for [1] seems to be completely missing the
| point, that Mozilla program isn't about funding an image host
| (yeah, I'd also prefer if Mozilla focused on the Browser and
| perhaps Thunderbird, but the foundation is what it is):
| https://news.ycombinator.com/item?id=41681666
| prism56 wrote:
| To be fair I've followed ente for a while and they seem to
| let their teams have side projects if it falls in line with
| the overall ente ethos.
|
| Same with Kagi. Thats where Kagi news was born.
|
| I quite like the ethos, but this Ensu definitely seems
| underbaked.
| moffkalast wrote:
| Probably just another ollama-type service who wants to slide
| themselves in between the user and local models, so they can
| take all the credit and work on convenience based platform
| lock-in, then later introduce paid tiers.
| BaudouinVH wrote:
| Installed it on a not-so-young laptop. It crashes immediately
| after launch. I blame the laptop.
|
| If Ente is reading this : please add requirements to make it run
| (how many RAM, etc.)
| xtracto wrote:
| I would love to see a "distributed LLM" system, where people can
| easily setup a system to perform a "piece" of a "mega model"
| inference or training. Kind of like SETI@home but for an open LLM
| (like https://github.com/evilsocket/cake but massive )
|
| Ideally if you "participate" in the network, you would get
| "credits" to use it proportionally to how much GPU power you have
| provided to the network. Or if you can't, then buy credits
| (payment would be distributed as credits to other participants).
|
| That way we could build huge LLMs that area really open and are
| not owned by any network.
|
| I would LOVE to participate in building that as well.
| xtracto wrote:
| Oh yeah, and maybe call it "SkyNet" or something.
| kennywinker wrote:
| https://docs.anarchai.org/
|
| This was posted the other day, but only briefly made the front
| page - seems kinda like what you're talking about
| xtracto wrote:
| Oooh thanks a lot. This looks promising. Maybe the only
| missing thing would be sone kind of (economic) incentive to
| share GPU power.
|
| Although the ability to use large models "for free" sounds
| pretty rad.
| kennywinker wrote:
| I'd volunteer my spare gpu time if i knew it was going to
| ... idk basically anyone except spammers, scammers, and
| corpos.
| xtracto wrote:
| That's why the _use_ has to have some kind of cost. Sure,
| spammers and scammers will always have spare money, as
| long as the bounty is higher.
|
| But the alternative is "not having Email", because Email
| can be used by the same bad actors.
| antipaul wrote:
| https://psyche.network/runs
| sbassi wrote:
| For local LLM there are Ollama and LM Studio. How is this
| different?
| kennywinker wrote:
| This seems like a great question to ask an offline llm that
| runs on your mobile device. Does ollama and Lm studio run on
| your mobile device?
| vvilliamperez wrote:
| I just use open claw as a local memory management system. Not
| sure from TFA what's new here.
| daikon899 wrote:
| The "What's next" section is more interesting than what shipped.
| A general-purpose chat wrapper around a 1-4B model occupies a
| crowded space -- PocketPal, Jan, LMStudio, GPT4All all do similar
| things. But the ideas they gesture at (a persistent "second
| brain" note, an LLM-backed launcher, long-term memory that grows
| with you) are actually differentiated
| pulkitsh1234 wrote:
| I am surprised to see this on HN front page, there is no new
| information here, just an ad.
| getpokedagain wrote:
| As someone who saw this and was interested but also skeptical of
| this being low effort are there other open projects for running
| small models locally on android / iOS?
|
| I've found https://github.com/alichherawalla/off-grid-mobile-ai
| but haven't tried anything in this space yet.
| stressback wrote:
| Google's AI Edge Gallery worked really well for me. It's still
| in early access.
| RandomGerm4n wrote:
| I like the idea of having a user-friendly app that lets you use
| LLMs locally. Tools like Ollama and LMStudio tend to put most
| people off because you have to decide for yourself which models
| to use and there are so many settings to configure. If the
| hardware you're using is compatible, Ensu could be a drop-in
| replacement for casual ChatGPT users.
|
| However, it's a bit confusing because, for example, a larger LLM
| model was downloaded to my smartphone than to my computer. It
| would probably make the most sense if the app simply categorized
| devices into five different tiers and then, depending on which
| performance tier a device falls into, downloaded the appropriate
| model and simply informed the user of the performance tier. Over
| time, it would then be possible to periodically replace the LLM
| for each tier with better ones, or to redefine the device
| performance tiers based on hardware advancements.
| drak0n1c wrote:
| Osaurus is what I use for local - it's a native Swift macOS app
| with sandboxing, agent tooling, and server capabilities. Mac
| only though.
| jimmyjazz14 wrote:
| LLMStudio is pretty darn easy and if I recall it recommends a
| model to install when you first start it
| selfawareMammal wrote:
| > People called us crazy.
|
| Absolutely no one called them crazy.
| razvan_maftei wrote:
| Looks like something spun up by Claude Code without thorough
| testing or design behind it sadly.
| tmanderson wrote:
| beware of data rackets
| socalgal2 wrote:
| What's special about Ente?
|
| How does it compare to Jan AI for example? or LM Studio? or ????
| alterom wrote:
| It's available on Android and iOS, and specifically on Play
| Store and Apple Store (so no "developer mode" hoops to jump
| through to install).
| buster wrote:
| I don't understand all the hate about ente, to be honest. Ente
| seems to try to solve the big tech lock in with their apps.
| Personally, i'm a very happy Ente Photos user, so what's the
| problem with Ensu? It's available on desktops and mobile, it's an
| app trying to give all a little bit more privacy and freedom and
| yet most comments are just hating on it. If you can vibe code
| Ensu in a week end, please do. Make a better clone if you want
| to, but don't hate on someone for their work for stupid reasons.
| alterom wrote:
| I think the hate boils down to _" I could've built it in a day
| with Claude, but didn't, so they suck"_ sour grapes.
|
| When the comments here say "there's no value because _anyone_
| could 've compiled llama.cpp", you can see how detached from
| reality these people are.
|
| Even jumping through the hoops to get an app on Play Store
| _and_ Apple Store -- an app that I can tell my friends to look
| up and download -- is worth a lot.
|
| An app that is _also_ is available on Mac and PC, mind you.
|
| I'm an ex-Google/Meta/Microsoft/Roblox software engineer, and I
| couldn't be bothered to do any of that.
|
| Neither could the rest of HN. But I'm not the one complaining
| about _lack of novelty_ or _value_ in this proposition.
| MillironX wrote:
| My personal gripe with Ente is that they seem to value making
| new half-baked products over making their current products
| feature-complete. Case-in-point: RAW photos are still not
| supported in Ente Photos [1]. Locker and now Ensu got priority
| over a key feature in making the Photos app a photos app.
|
| [1]: https://github.com/ente-io/ente/discussions/625
| todotask2 wrote:
| Model is last trained on Dec 2023, that's consider outdated.
| georaa wrote:
| Smart move building on local models. The privacy argument is real
| but I think the bigger win is latency - no round trip to an API
| means you can do things like inline suggestions that would feel
| sluggish over the network.
| sneak wrote:
| Meanwhile, my Ente photos app crashes 20 times a day on iOS when
| using advanced functionality such as scrolling through my photos.
|
| They also have a TOTP auth app?
|
| If their photos app stopped crashing and they pursued basic
| feature parity between their iOS and desktop apps (IMO table
| stakes for a photo sync service) I'd have no issue recommending
| them. Instead, it seems like every so often they just branch off
| into a new direction, leaving the existing products unfinished.
| It's like Mozilla-level lack of focus.
___________________________________________________________________
(page generated 2026-03-25 23:00 UTC)