ESP32s3 LLM Cluster
Seven ESP32-S3s daisy-chained to run a 0.4B ternary LLM.
By Low-Zi-Hong
- Est. cost
- Cost unknown
- Posted
- GitHub stars
- 234 (GitHub)
Overview
A distributed inference engine that runs a sliced 0.5B 1.58-bit (BitNet) language model across a cluster of seven ESP32-S3 microcontrollers.
How it works
A master node runs the tokenizer and embeddings, and the other six run the attention and MLP layers in a pipeline. The boards pass activations over a high-speed SPI daisy chain. It builds on earlier single-node and distributed ESP32-S3 LLM experiments.
Hardware
- 7x ESP32-S3 over SPI
This page is a short summary written by HardwareLab. Build steps, code and photos belong to the creator; follow “View original” for the full project.
More in Local LLM Rigs & Edge Agents
See all 17Esp32 Iphone Agent
A $7 ESP32 lets an AI drive a real iPhone via AirPlay and USB HID.
- ESP32 (USB HID)
- iPhone
IntermediateCost unknown1.4KPocket Tank
A 14M-parameter LLM keeps a virtual fish tank alive on an $8 ESP32.
- ESP32-S3
AdvancedCost unknown207Needle 2 Esp32
45M-parameter LLM offline on an ESP32-S3 turning English into valid commands.
- ESP32-S3
AdvancedCost unknown193