Yet another Hacker News

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

71 points logicallee 2 hours ago 20 comments

logicallee 2 hours ago | parent

You can try 7 different tiny LLM's in your browser.

bigfishrunning 1 hour ago | parent

What I missed from the title was this: Can I try 7 different tiny LLMs in my browser?

tnrich 1 hour ago | parent

i have a bromine tub, give me simple instructions for what to do since i just filled it up w fresh water

1. Add 1 tablespoon of water to the water bath. 2. Place the tub into the water bath and let it sit for about 5 minutes. 3. After 5 minutes, remove the tub and let it cool down. 4. Now, fill the tub with water and let it sit for about

uhmm completely unusable ?

smokel 1 hour ago | parent

No, that is not what SLMs are useful for. They have very little knowledge, and typically lack reasoning skills.

Useful applications include sentiment analysis, text classification, entity extraction, etc.

They certainly can be useful, but you shouldn't compare them with LLMs such as Opus or Fable.

ironqcold 47 minutes ago | parent

Completely unusable for that, yeah, that's a 100M model, not an assistant

AgentMasterRace 1 hour ago | parent

The website literally says they are SLM's .. derp af

tolugenius 1 hour ago | parent

I did the default arithmetic with PetitGPT research-v1

>What is 2+2?

Answer

> To find 2 + 2, we need to add 2 to both sides of the equation.

> 2 + 2 = 4

> So, 2 + 2 = 4 + 2.

Brilliant

bhouston 58 minutes ago | parent

I built something like this just last month, using a few of the same models, but I used ThreeJS's Three-Shading-Language abstraction to do it: https://three-llm.ben3d.ca/?model=qwen3.5-0.8b

jellyfiz 57 minutes ago | parent

Similarly, if someone wants to hack some LLMs in their browser and burn some cycles, please feel free to try to break them here:

https://ai-attacks.neal.codes/

demibabs 43 minutes ago | parent

Cool project, but I'd really suggest looking at the UI.

The text is too small and it's way too dense with information in general. Considering how simple this product is to use, it's kinda crazy that I have to scroll through over a page length of (mostly useless, AI-generated) information before getting to the actual interface.

Also what is going on with the footer (why does it link back to the site itself, why is it telling me to "serve over HTTP").

phist_mcgee 2 minutes ago | parent

This is the future of software, sloppy ui.

derliebej 40 minutes ago | parent

Wouldn't that be a TLM?

vs4vijay 36 minutes ago | parent

I have been experimenting with something similar here - https://sonistellar.com/lab/

inventor7777 31 minutes ago | parent

PetitGPT told me that

> "2+2 is 2."

Otherwise, a very neat demo. As others have said, the UI is VERY confusing, way too much stuff going on.

dvh 20 minutes ago | parent

It is. For very small values of 2.

kenzic 22 minutes ago | parent

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: https://www.webmodels.dev

logicallee 12 minutes ago | parent

I read your proposal, I think it'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.

kenzic 6 minutes ago | parent

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?

anonimous-emacs 19 minutes ago | parent

unfortunately on firefox: Uncaught ReferenceError: GPUShaderStage is not defined

willaaam 19 minutes ago | parent

I like it as I'm vibecoding an (airgappable) browser AI workspace myself, but in terms of putting the models to use, just exposing the chat interface feels a bit limiting to me.

My take on this concept: https://github.com/willaaam/gemma-4-E2B-webgpu-vision