28.9M-parameter LLM runs locally on ESP32-S3 at 9 tokens/s

Source: CNX Software· Jean-Luc Aufranc (CNXSoft)· August 3, 2026
28.9M-parameter LLM runs locally on ESP32-S3 at 9 tokens/s

Slava S. (slvDev) has optimized a 28.9M-parameter LLM running locally on an ESP32-S3 development board at around 9 tokens/s while generating text, or more exactly, telling short stories. We've written about LLMs and ESP32 in the past, but usually the boards a…

This story was reported by CNX Software. Read the full original article:
Read on CNX Software

More in Products & Launches

View all