wladimiravila/esp32s3-distributed-ai

Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.

2 best points · 2 comments · 1 Hacker News post · 115 GitHub stars · View on GitHub

Hacker News discussions

• HN: I ran a 56M parameter LLM across three ESP32-S3 boards via ESP-NOW (2 points, 2 comments, by wladimiravila, 2026-07-30)