Hackster.io

@hacksterio · Twitter · 2026-08-01 20:15 UTC

A developer borrowed a trick from Google's Gemma models to fit a 28.9M parameter LLM on an $8 ESP32 chip. https://www.hackster.io/news/running-a-28-9m-parameter-llm-on-an-8-microcontroller-173f1f370708