‹ BackHN Continuity

Thread

MicroLLM Lab – Try 7 tiny LLM's in the browser

283 points · 113 comments · logicallee

  1. kenzic · · focus · HN ↗
    Really cool project. Giving web apps direct access to on-device models is something I’m excited about, and it’s cool to see the different approaches.

    I’ve been working on a related proposal called the Web Models API, which explores a browser standard for an API that runs open-weight models on-device. Would love your thoughts: <a href="https:&#x2F;&#x2F;www.webmodels.dev" rel="nofollow">https:&#x2F;&#x2F;www.webmodels.dev

    1. logicallee · · focus · HN ↗
      I read your proposal, I think it&#x27;s great! Where will the navigator get the model if the user agrees to download it? For this demonstration I just serve the models on my own server, but for larger models it may be an issue as they may not have direct download links even if they are open weights.
      1. kenzic · · focus · HN ↗
        Great question. Right now there isn’t a definitive answer, but it’s something that needs to be worked out. There would likely be a registry. The question is how to keep model IDs consistent: does each browser manage its own registry, or is there one shared across browsers?
        1. logicallee · · focus · HN ↗
          Since you&#x27;re asking for some kinds of permissions anyway, you could ask if the user is willing to also seed the model, p2p. (However, seeding files is not as popular as it used to be, many residential Internet connections don&#x27;t have good upload.) If you have the capacity for it, your site webmodels.dev could act as a tracker and initial seed for any models. Then it could be the one central registry. It might get to be too much for you though, a lot of the open weights models are huge.
          1. kenzic · · focus · HN ↗
            Interesting idea. I hadn&#x27;t considered that. Thanks
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.