8-Dollar ESP32-S3 Microcontroller Runs 28.9M-Parameter LLM

A developer ran a 28.9M-parameter LLM on an 8-dollar ESP32-S3 microcontroller, achieving 9.5 tokens/s inference speed fully offline. The open-source project demonstrates low-cost edge AI capabilities.

2026-07-29 ~ 2026-07-30 · 3 related posts

• An $8 ESP32-S3 now runs a 28.9M-parameter LLM fully offline — nikola_mr64990 · 2026-07-29
• Open-Source LLM Runs Locally on an $8 Microcontroller at 9.5 Tokens/Sec — Saboo_Shubham_ · 2026-07-30
• Running a 28.9M Parameter LLM on an $8 Microcontroller at 9 Tokens/s — Saboo_Shubham_ · 2026-07-30