Atome LM, an AI that runs on A $5 ESP32. No internet, no os, no data center.

A lightweight language model, Atome LM (944K parameters) has been successfully run on a $5 ESP32-WROOM-32 microcontroller — not in simulation, but on real hardware. The model generates text offline at about 1 token per second, proving that LLM inference is possible on tiny chips without cloud support.

For the little details and Open Source GitHub :

https://atomelm.com/blog/atome-runs-on-a-physical-esp32.html

https://github.com/TilelliLab/atome-lm

What do you think ?