Low-Zi-Hong/ESP32s3-LLM-Cluster

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

a Transformer Based Model for ESP32 (520KB Memory)

Running a LLM on the ESP32

Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

A ternary, zero-heap tiny language model that runs inside a $2 microcontroller — bit-exact Python <-> C99 <-> Cortex-M3 (QEMU) parity. Apache-2.0.

MimiModel: Agentic LLM on a $5 chip. 100% on-device. Private by design.

[Official] Prima.cpp: Scale Your Local AI Beyond One Device.