Starred repositories
3
stars
written in C
Clear filter
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
Run large AI models across your computers and servers. Powered by Colibri. Pure C.