ESP32S3 cluster running 1.58-bit (BitNet) Language model
nkko
68 points
9 comments
September 28, 2026
Related Discussions
Found 5 related stories in 80.4ms across 7,945 title embeddings via pgvector HNSW
- Running a 28.9M parameter LLM on an $8 microcontroller boveyking · 131 pts · July 25, 2026 · 58% similar
- Breaking the 1.58-bit Barrier for Ternary LLMs matt_d · 177 pts · September 16, 2026 · 48% similar
- Show HN: I'm Serving Esp32s31.fun abu-matterize · 14 pts · September 14, 2026 · 46% similar
- Show HN: A tiny LLM running at 21,000 tok/s on a $250 FPGA (Live Demo) mikeayles · 12 pts · August 10, 2026 · 45% similar
- MicroLLM Lab – Try 7 tiny LLM's in the browser logicallee · 198 pts · September 28, 2026 · 44% similar
Discussion Highlights (6 comments)
cameron_b
It is a bit of a bummer to see that the degree of 'compression' makes it a fancy llm noise-maker. It is still charming.
sjakati98
Gemma 4 when?
tdhz77
Soon ai in every lightbulb running Kubernetes
matthewfcarlson
I’m actually working on a small project that’s exactly this! Less quant so it’s only 150M parameters but this is amazing.
NDlurker
I'm curious how this would handle grammar checking on a basic word processor. Or maybe generate worlds for small text based games. I have no idea what the capabilities are of a cluster like this.
nonasking_
Thanks for sharing. It's fascinating to see a 0.5B LLM being split across seven ESP32s like this.