ESP32S3 cluster running 1.58-bit (BitNet) Language model (github.com)

71 points by nkko 9 hours ago

12 comments:

by librasteve 17 minutes ago

haha … this is precisely the kind of project that https://bil-lang.org is aimed at: Go for parallel (ie in this case pipeline processing).

don’t get too excited until we get the TinyGo backend built though ;-)

by tdhz77 4 hours ago

Soon ai in every lightbulb running Kubernetes

by oneZergArmy 20 minutes ago

Praise the Omnissiah.

by tombert 2 hours ago

You know, I've always liked Futurama but I always kind of thought it was silly that literally everything has an AI and a personality.

But, you know, I actually think that there might be a logic to it. Economies of scale might mean that almost-literally every computer you buy in the year 3000 has some kind of AI-assistance chip in there, and sure maybe it will have full AI with a personality spitting out one-liners.

by KeplerBoy 19 minutes ago

Change the year 3000 to the 2030s and it might be just as accurate.

by abroadwin an hour ago

Kind of like how disposable vape pens often have a 24 MHz Cortex-M0+ with 3 kB SRAM and 24 kB flash, which would have seemed ludicrous a while back.

by NDlurker 3 hours ago

I'm curious how this would handle grammar checking on a basic word processor. Or maybe generate worlds for small text based games. I have no idea what the capabilities are of a cluster like this.

by cameron_b 6 hours ago

It is a bit of a bummer to see that the degree of 'compression' makes it a fancy llm noise-maker. It is still charming.

by matthewfcarlson 3 hours ago

I’m actually working on a small project that’s exactly this! Less quant so it’s only 150M parameters but this is amazing.

by nonasking_ 2 hours ago

Thanks for sharing. It's fascinating to see a 0.5B LLM being split across seven ESP32s like this.

by sjakati98 5 hours ago

Gemma 4 when?

by nkozyra 2 hours ago

We're gonna need a bigger ESP.

Data from: Hacker News, provided by Hacker News (unofficial) API