colibri: Pure-C Zero-Dependency Engine Streams MoE Experts From Disk to Run Frontier Models Locally

JustVugg · github · 2026-09-10

colibri, trending on GitHub with 27K+ stars, is a tiny pure-C inference engine with zero dependencies that runs frontier MoE models on hardware you already own.

The trick: expert weights are streamed from disk on demand instead of residing in memory, sidestepping VRAM/RAM capacity limits. "Tiny engine, immense model" — a notable entry in the local-inference space.

Original post →

More from Infra

Infra channel →