colibrì
Apache-2.0 pure-C zero-deps MoE streamed from disk
AI Agents / Tooling · Apache-2.0 · 42.8k
Reviewed 2026-09-16 · last push 2026-10-19 · repo checked 2026-10-19
What's Good
Apache-2.0 (JustVugg/colibri). Single-file C engine with disk/RAM/VRAM multitiering for huge MoE families (GLM-class and cousins). `coli chat` / `coli serve` / `coli web`. No BLAS, no Python at engine runtime. Site at justvugg.github.io/colibri. Prebuilt releases for Linux/macOS/Windows.
The Catch
Vs Ollama/vLLM (local serve / high-throughput GPU serving): colibrì is research-grade MoE disk-streaming for models that do not fit, not the everyday pull-and-chat DX of Ollama or the production serving stack of vLLM. research/HW-heavy — expect fast NVMe, large model containers (hundreds of GB), and tokens/sec that track your disk hierarchy.
Verdict
Apache-2.0 pure-C MoE engine. Disk-streamed experts vs Ollama/vLLM; hardware-honest.
Embed
Maintainer? Add the badge to your README. It is free, links to this review, and there is no paid version.
Markdown
[](https://stackgems.com/gems/colibri)
HTML
<a href="https://stackgems.com/gems/colibri"><img src="https://stackgems.com/badge/colibri.svg" alt="colibrì reviewed on Stack Gems" height="20"></a>