Hacker News Reader

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

You mention "most of them" were not generating good recipes. Did any of them give you a usable recipe?

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

I've tried to fix this, please check again. Thank you.

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

Thank you. I've tried to fix this, could you please check again?

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

I've tried to fix this, please check again, thank you.

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

Great, thank you for making it and also the fixes!

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

I've tried to fix it, let me know if there is still an issue.

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

I've tried to fix the Firefox on Linux issue, can you check again? Firefox doesn't have WebGPU enabled by default on Linux so you will have to use the wasm fallback which is slower.

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

I've made it more clear what parts are optional reading. summary of my changes here: https://news.ycombinator.com/item?id=49897068

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

All right, I've made some of the requested changes, summarized here: https://news.ycombinator.com/item?id=49897068

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

I've thought some more about your feedback, since other replies gave the same feedback. At the same time, I didn't want to remove the "mostly useless" information since clearly it was useful for a lot of people! The submission was on the front page of HN (often in the #3 or #4 spot) for 12 hours and last I checked generated more than 300,000 requests from 36,000 unique IP's (on an ordinary 2-day period there are around 1,600 unique IP's) and people downloaded 600 GB of models, including 8.5k downloads initiated for the first model (3,000 of which were completed and 5.5k of which did not wait for it to complete, since download was a little slow due to the high number of concurrent users.)

So, clearly, the presentation format resonated with a lot of people. Therefore, I kept the presentation but put a tl;dr in enormous can't-miss-it shimmering font at the top. I marked all the "dense information" you mentioned as "Optional reading" (it's a lab after all, there should be a reading for it) and increased the font size.

I removed the parts of the footer that you said didn't make sense. The page isn't on the front page anymore so I don't know if people would like the changes or not, but I've changed the page layout in response to your feedback.

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

Could I ask what browser, operating system, and GPU you use? In my testing they do not fall into a loop, maybe there is an error that affets how it's being run on your device.

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

They probably flagged it because they thought an LLM wrote my comment, perhaps because of the disconnect between my initial reply and the edit. Together with the whole comment, the first part of my reply sounds like it could have been written by an LLM.

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

Thanks for trying it! These models are really tiny, I wouldn't expect them to be able to answer about javascript keypresses. I'm surprised that, as you mentioned, the Smol model was able to answer correctly!

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

I think you've fixed it! I just tested it, now it works. (In both Chrome on Windows with NVidia 1060 gpu w/ 6 GB vram, which is what it wasn't working on yesterday, and on Safari on 2026 Mac Mini M4 with 24 GB of RAM. The former is pretty slow, around 1 tok/sec, the latter is fast at 18 tok/sec.)

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

Thanks for sharing. I tried the online demo, which downloaded the model but, unfortunately, couldn't start it. (It says " Invalid magic number Make sure your local server is running and CORS is enabled.")

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

Sorry. That shouldn't happen. It doesn't use a lot of memory and only uses WebGPU in the normal way. What version of macOS and Safari did you use, and what is your hardware, please?

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

Interesting project, thanks for sharing.

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

I tried the Python and SQLite modules on desktop Chrome and got similar errors for both. For Python:

Error: CPython engine could not load (Failed to fetch dynamically imported module: https://sonistellar.com/lab/vendor/pyodide/pyodide.mjs). Check the network, then close this tile and re-boot to retry. — press reset or back to menu

For SQLite:

Error: SQLite engine could not load (GET https://sonistellar.com/lab/vendor/sqlite/sql-wasm.js -> HTTP 404). Check the network, then close this tile and re-boot to retry. — press reset or back to menu

FreeDOS loaded though, Snake and Tetris were fun!

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

In this particular case it used to not have any text at the top. Just click a model, chat.

I decided that that wasn't very user friendly. It doesn't tell people what it is. Or how to use it. It doesn't explain any of the concepts or vocabulary.

So I asked it to add those things, above the main interface, including the steps people need to take to use it. I think it did great, and I think the small text sizes with a clear title let people who need it, read it, and people who don't can just scroll down. Even with the text it's 600 words.

I like the effect of what it's done. It's better than I would have done if I had written those intro words myself.

Clearly it resonates with people, this thing has been on the front page of HN for 4 hours and with 110 points is by far the most popular thing I've ever posted here.

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

This is a difficult one for me to fix since I don't have a Radeon GPU. I'll see if there is anything I can do tomorrow.

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

It's a cool idea. I'm on my phone now (going to sleep soon), a few of the demos didn't boot on this device. I'll check from desktop tomorrow.

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

Thanks. Unfortunately it's too late to change the title!

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

It's a cool project, but I couldn't get it to load. What did you test this on? I tried the live link here:

https://willaaam.github.io/gemma-4-E2B-webgpu-vision/

And after loading it, with an NVidia 1060 GPU (6 GB RAM) on Windows it failed with "Failed to load: No supported WebGPU variant for com.xenova.gemma4.DenseGemv; rejected sgma".

In Safari on a 2026 Mac Mini M4 with 24 GB of RAM it failed with "Failed to load: JSON Parse error: Unexpected EOF".

The idea is pretty cool though!

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

Awesome! I tried it and after loading (which took a while as it is a large model) got 12 tokens/second and very coherent output. Great demonstration.

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

That one is a 2019 model :) Years before the ChatGPT public preview.

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

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!

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

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.)

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

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.)

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

Since you'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'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.

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

I got the correct output for PetitGPT research-v1: https://ibb.co/0pP9DS2T