MicroLLM Lab – Try 7 tiny LLM's in the browser (stateofutopia.com)
90 points by logicallee 3 hours ago
demibabs 2 hours ago
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").
logicallee an hour ago
Thank you for the feedback, I'll think about how to incorporate the changes you've suggested.
phist_mcgee an hour ago
This is the future of software, sloppy ui.
tolugenius 2 hours ago
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
dotancohen an hour ago
That's not incorrect.
LLMs produce semantically correct sentences, not factually correct statements. Have we forgotten this so soon?
anyfoo an hour ago
It is, in every sense, incorrect. Which statement in this short snippet is "semantically correct"? (Better LLMs get this right, of course.)
tecleandor 43 minutes ago
GPT-2 124M is terrible...
> what is 2+2?
> 3+3? 4+4? 5+6? 7+8?
> Reply ~18000 0 ~10 min 2 By : 1-1: I'm a beginner. 3x2 is my best option, but if you're not sure about the other options then just go for it and try againkrackers 40 minutes ago
It's not instruct tuned looks like? It's closer to a base model rather than a chatbot.
logicallee 11 minutes ago
logicallee 11 minutes ago
GPT-2 is an interesting one because it is a February 2019 model. (You can see some information about it below the card if you click on the card.)
That was 2-3 years before the big "ChatGPT moment" (the highly coherent ChatGPT research preview was released in November 2022, I think it was ChatGPT 3.5). Back in 2019 the models really were not producing very coherent output. Now you can see it for yourself right in your browser :) Everything has come a really long way since then!
logicallee an hour ago
I got the correct output for PetitGPT research-v1: https://ibb.co/0pP9DS2T
mgaunard 16 minutes ago
> how would you compare your capabilities to that of claude fable 5.1 by anthropic
> Comparing your capabilities to that of claude fable 5.1 would be very similar. Both are stories about a clown who is a cunning and manipulative animal. They both have problems and challenges, and they face challenges to overcome them. However, they have different goals and approaches. The clown
I think that tells you all you need to know.
kenzic 2 hours ago
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 an hour ago
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 an hour ago
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?
logicallee 36 minutes ago
micw 9 minutes ago
It's LLMs, not LLM's ;-)
willaaam an hour ago
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
bhouston 2 hours ago
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
vs4vijay 2 hours ago
I have been experimenting with something similar here - https://sonistellar.com/lab/
jellyfiz 2 hours ago
Similarly, if someone wants to hack some LLMs in their browser and burn some cycles, please feel free to try to break them here:
inventor7777 2 hours ago
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 an hour ago
It is. For very small values of 2.
anonimous-emacs an hour ago
unfortunately on firefox: Uncaught ReferenceError: GPUShaderStage is not defined
logicallee 25 minutes ago
I tested it on Firefox on windows, version 156.0.1 and didn't get that error.
What version of Firefox are you using and what is your operating system and graphics card, please? Can you also try it without WebGPU? (Reload the page and uncheck "Prefer WebGPU" and try a prompt.)
rvz 42 minutes ago
Nothing on this site actually works.
logicallee 29 minutes ago
What browser are you using? I tested it on Windows, Mac, and iPhone. I tested it in Chrome, Firefox, Edge, and Safari. Everything works on the three machines and phone I tested it on.
(It's a little bit slow at the moment - you have to wait a few seconds for the models to load - as it's currently on the HN front page. The server is on a 1 gigabit unmetered network connection so it can serve all the weights - around 600 megabytes - to one person every few seconds, there are several concurrent users now.)
fragmede 20 minutes ago
serve the models via CDN?
derliebej 2 hours ago
Wouldn't that be a TLM?
tnrich 2 hours ago
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 2 hours ago
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 2 hours ago
Completely unusable for that, yeah, that's a 100M model, not an assistant
logicallee 3 hours ago
You can try 7 different tiny LLM's in your browser.
bigfishrunning 2 hours ago
What I missed from the title was this: Can I try 7 different tiny LLMs in my browser?
AgentMasterRace 2 hours ago
The website literally says they are SLM's .. derp af