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.
More from Infra
- PyTorch details 2.12x faster on-device streaming ASR on Arm SME2 via ExecuTorch — PyTorch · 2026-10-27
- Revenue per GPU can rise as token prices fall, argues Gavin Baker — GavinSBaker · 2026-10-27
- Anthropic S-1: only $19B total compute spend since inception, overbuild warning — bookwormengr · 2026-10-27
- CoreWeave, You.com and NVIDIA lift BrowseComp 22.9% in 3-week RL post-training sprint — RichardSocher · 2026-10-27
- Grid queues make power architecture an AI-factory decision; Exowatt and Redwood offer fixes — ingliguori · 2026-10-27
- Two CVSS 9.9 Wasmtime flaws allow sandbox escape, one ARM64-only since 2020 — basedjensen · 2026-10-27