[HN Gopher] Google AI Edge - On-device cross-platform AI deployment
       ___________________________________________________________________
        
       Google AI Edge - On-device cross-platform AI deployment
        
       Author : nreece
       Score  : 157 points
       Date   : 2025-06-01 06:32 UTC (16 hours ago)
        
 (HTM) web link (ai.google.dev)
 (TXT) w3m dump (ai.google.dev)
        
       | davedx wrote:
       | More information here:
       | https://ai.google.dev/edge/mediapipe/solutions/guide
       | 
       | (It seems to be open source: https://github.com/google-ai-
       | edge/mediapipe)
       | 
       | I think this is a unified way of deploying AI models that
       | actually run on-device ("edge"). I guess a sort of "JavaScript of
       | AI stacks"? I wonder who the target audience is for this
       | technology?
        
         | wongarsu wrote:
         | Some of the mediapipe models are nice, but mediapipe has been
         | around forever (or 2019). It has always been about running AI
         | on the edge, back when the exciting frontier of AI were visual
         | tasks.
         | 
         | For stuff like face tracking it's still useful, but for some
         | other tasks like image recognition the world has changed
         | drastically
        
         | babl-yc wrote:
         | I would say the target audience is anyone deploying ML models
         | cross-platform, specifically ones that would require supporting
         | code beyond the TFLite runtime to make it work.
         | 
         | LLMs and computer vision tasks are good examples of this.
         | 
         | For example, a hand-gesture recognizer might require: - Pre-
         | processing of input image to certain color space + image size -
         | Copy of image to GPU memory - Run of object detection TFLite
         | model to detect hand - Resize of output image - Run of gesture
         | recognition TFLite model to detect gesture - Post processing of
         | gesture output to something useful
         | 
         | Shipping this to iOS+Android requires a lot of code beyond
         | executing TFLite models.
         | 
         | The Google Mediapipe approach is to package this graph
         | pipeline, and shared processing "nodes" into a single C++
         | library where you can pick and choose what you need and re-use
         | operations across tasks. The library also compiles cross-
         | platform and the supporting tasks can offer GPU acceleration
         | options.
         | 
         | One internal debate Google likely had was whether it was best
         | to extend TFLite runtime with these features, or to build a
         | separate library (Mediapipe). TFLite already supports custom
         | compile options with additional operations.
         | 
         | My guess is they thought it was best to keep TFLite focused on
         | "tensor based computation" tasks and offload broader operations
         | like LLM and image processing into a separate library.
        
       | yeldarb wrote:
       | Is this a new product or a marketing page tying together a bunch
       | of the existing MediaPipe stuff into a narrative?
       | 
       | Got really excited then realized I couldn't figure out what
       | "Google AI Edge" actually _is_.
       | 
       | Edit: I think it's largely a rebrand of this from a couple years
       | ago: https://developers.googleblog.com/en/introducing-
       | mediapipe-s...
        
       | rvnx wrote:
       | Make your own opinion here: https://mediapipe-
       | studio.webapps.google.com/studio/demo/imag...
       | 
       | Go to this page using your mobile phone.
       | 
       | I am apparently a doormat or a seatbelt.
       | 
       | It seems to be a rebranded failure. At Google you get promoted
       | for product launches because of the OKRs system and more rarely
       | for maintenance.
        
         | tfsh wrote:
         | Perhaps you missed the associated documentation? This is a
         | classification tool which requires input labels "uses an
         | EfficientNet architecture and was trained using ImageNet to
         | recognize 1,000 classes, such as trees, animals, food,
         | vehicles".
         | 
         | The full list [1] doesn't seem to include a human. You can
         | tweak the score threshold to reduce false positives.
         | 
         | 1: https://storage.googleapis.com/mediapipe-
         | tasks/image_classif...
        
           | rvnx wrote:
           | You're right about human, that would explain it, but still I
           | find it surprising that such "common item" as a human is not
           | there.
           | 
           | Did you also try on items from the list ?
           | 
           | If there is a match (and this is not frequent), to me it's
           | still very low confidence (like noise or luck).
           | 
           | It seems to be a repacking of
           | https://blog.tensorflow.org/2020/03/higher-accuracy-on-
           | visio...
           | 
           | So an old release from 5 years ago (like very long time in
           | AI-world), and AFAIK it has been superseded by YOLO-NAS and
           | other models. MediaPipe feels really old tool, except for
           | some specific subtasks like face tracking.
           | 
           | And as a side-note, the OKR-system at Google is a very
           | serious thing, there are lot of people internally gaming the
           | system, and that could explain why it is a "new" launch,
           | instead of a rather disappointing rebrand of the
           | 2020-version.
           | 
           | I'd rather recommend building on more modern tools, such as: 
           | https://huggingface.co/spaces/HuggingFaceTB/SmolVLM-256M-Ins.
           | .. (runs on iPhone with < 1GB of memory)
        
             | bigyabai wrote:
             | > And as a side-note, the OKR-system at Google is a very
             | serious thing, there are lot of people internally gaming
             | the system.
             | 
             | So you came here to offer a knee-jerk assessment of an AI
             | runtime and blamed the failure on OKRs. Then somebody
             | points out that your use-case isn't covered by the model,
             | and you're looping back around to the OKR topic again. To
             | assess an AI inference tool.
             | 
             | Why would you even bother hitting reply on this post if you
             | don't want to talk about the actual topic being discussed?
             | "Agile bad" is not a constructive or novel comment.
        
       | danielb123 wrote:
       | Years behind what is already available through frameworks like
       | CoreML and TimyML. Plus Google has to first prove they won't kill
       | the product to meet the next quarterly investor expectations.
        
         | spacecadet wrote:
         | Its just a rebranded tensorflow lite, Ive been using that on
         | edge devices since 2019... CoreML is great too!
        
         | babl-yc wrote:
         | This isn't really true. They are different offerings.
         | 
         | CoreML is specific to the Apple ecosystem and lets you convert
         | a PyTorch model to a CoreML .mlmodel that will run with
         | acceleration on iOS/Mac.
         | 
         | Google Mediapipe is a giant C++ library for running ML flows on
         | any device (iOS/Android/Web). It includes Tensorflow Lite (now
         | LiteRT) but is also a graph processor that helps with common ML
         | preprocessing tasks like image resizing, annotating, etc.
         | 
         | Google killing products early is a good meme but Mediapipe is
         | open source so you can at least credit them with that.
         | https://github.com/google-ai-edge/mediapipe
         | 
         | I used a fork of Mediapipe for a contract iOS/Android computer
         | vision product and it was very complex but worked well. A
         | cross-platform solution would not have been possible with
         | CoreML.
        
           | NetOpWibby wrote:
           | I wish MediaPipe was good for facial AR but in my experience
           | it's lacking.
        
         | bigyabai wrote:
         | My brother in Christ, CoreML only exists because Apple saw
         | Tensorflow and wanted the featureset without cooperating on a
         | common standard. TF was like 2 years old (and fairly
         | successful) by the point CoreML was _announced_. To this day
         | CoreML is little more than a proprietary BLAS interface, with
         | nearly zero industry buy-in.
         | 
         | Terrifying what being an iOS dev does to a feller.
        
         | elpakal wrote:
         | The generative AI piece is not available in Apple ecosystems
         | right? I think that would be huge and I really hope Apple gives
         | us something similar. And I gotta say the chat piece of this
         | seems really useful too.
         | 
         | Also where the f is Swift Assist already
        
         | mattnewton wrote:
         | Tensorflow light has been battle tested on literal billions of
         | devices over the years and this looks like a rebrand/extension
         | of that plus media pipe, one of the biggest users of it. Google
         | has been serious about on device ML for over 5 years now, I
         | don't think they are going to kill this. Confusingly rebrand it
         | maybe :)
        
       | zb3 wrote:
       | So can we run Gemma 3n on linux? So much fluff yet this is
       | unclear to me.
        
         | quaintdev wrote:
         | As far as I know it's based on Gemini nano architecture which
         | exclusively runs on Android and Chrome. So I'm guessing you
         | can't run it on Linux outside Chrome.
        
         | saratogacx wrote:
         | In the model's community section Goog confirms they're working
         | on a gguf version so you can host it like most other models.
         | 
         | https://huggingface.co/google/gemma-3n-E4B-it-litert-preview...
        
       | ricardobeat wrote:
       | This is a repackaging of TensorFlow Lite + MediaPipe under a new
       | "brand".
        
         | echelon wrote:
         | The same stuff that powers this?
         | 
         | https://3d.kalidoface.com/
         | 
         | It's pretty impressive that this runs on-device. It's better
         | than a lot of commercial mocap offerings.
         | 
         |  _AND_ this was marked deprecated /unsupported over 3 years ago
         | despite the fact it's a pretty mature solution.
         | 
         | Google has been sleeping on their tech or not evangelizing it
         | enough.
        
       | hatmanstack wrote:
       | Played with this a bit and from what I gathered it's purely a re-
       | arch of pytorch models to work as .tflite models, at least that's
       | what I was using it for. It worked well with a custom finbert
       | model with negligible size reduction. It converted a quantized
       | version but outputs were not close. From what I remember of the
       | docs it was created for standard pytorch models, like
       | "torchvision.models", so maybe with those you'd have better luck.
       | Granted, this was all ~12 months ago, sounds like I might have
       | dodged a pack of Raptors?
        
       | stanleykm wrote:
       | i really wish people who make edge inference libraries like this
       | would quit rebranding them every year and just build the damn
       | things to be fast and small and consistently updated.
        
         | bigyabai wrote:
         | ONNX exists but since they don't change their name very often
         | not a whole lot of people know about it.
        
       | arbayi wrote:
       | https://github.com/google-ai-edge/gallery
       | 
       | A gallery that showcases on-device ML/GenAI use cases and allows
       | people to try and use models locally.
        
       | fdoifdois wrote:
       | Related: https://stackoverflow.com/q/79454372/320615
        
       | roflcopter69 wrote:
       | Genuine question, why should I use this to deploy models on the
       | edge instead of executorch? https://github.com/pytorch/executorch
       | 
       | For context, I get to choose the tech stack for a greenfield
       | project. I think that executor h, which belongs to the pytorch
       | ecosystem, will have a way more predictable future than anything
       | Google does, so I currently consider executorch more.
        
       ___________________________________________________________________
       (page generated 2025-06-01 23:00 UTC)