Open Source Pulse
serphen avatar

serphen/microkimi

Rust

Run and train your own miniature Kimi K3: a zero-dependency Rust inference engine, reimplemented from scratch - and nanokimi, a small model trained from scratch on CPU by the included training pipeline. Talks straight to the Metal API for GPU on macOS - CPU mode stays the fastest at small model sizes.

+10 today 10 total stars

Star History

10 10 11 11 11
from-scratch inference-engine kimi linear-attention llm machine-learning mixture-of-experts moe mxfp4 rust tiktoken zero-dependency
Quality 100 🔥 21