Running a 28.9M parameter LLM on an $8 microcontroller (github.com)

9.7 tokens/sec actually seems like a lot! That’s fun!

This is a really cool project. Thanks for sharing!

This is a really neat use of the per-layer embedding trick. It's also worth noting that there viable TTS models that are ~20-30M param, so it might mean you can have a ESP32 with no network access read stuff out to you in near real time!

Why can't this scale to run much larger models on CPU backed by flash with good access patterns?

Super cool, thank you for sharing!

>esp32-s3

This microcontroller is a beast, currently using it to do dev work on a pi4.

Having two usb ports with one otg lets you do some neat things that would cost $100+ otherwise

It's crazy what $5 can buy you in a microcontroller these days. Have a look at these Milk-V boards:

https://milkv.io

The duo has up to 256MB of memory, and a 1TOPS@INT8 TPU. They run Linux and are $5. I bought 5!

Finally, an LLM that can run on my i5

While running LLM on tiny device is awesome, I'm more impressed by whatever training has produced the weights

Pretty incredible performance for the footprint - really interested to see what could be done on slightly more powerful SBCs like some that have been mentioned in this thread.

Voice-to-Text and Text-to-Voice models are approaching that size. I wonder how close we are to getting small devices that can chat with us.

Imagine a world where your toothbrush could give you tips about dental hygiene - or advertise toothpaste. What a time to be alive!

How lovely j

Wont this wear out the flash memory quickly? I wonder hiw many read cycles can it survive

How accurate is this quantized model?

i don't care about microcontroller, what is the decent option to have local llm in my raspi4 that does not take 30 seconds to answer?

[dead]

[dead]

[flagged]