Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Tiny engine, immense model. colibri runs very large open models on the machine you already have. A mixture-of-experts model of hundreds of billions of parameters uses only a small part of itself for each token, so colibri keeps that part in RAM and reads the rest, the experts, from the disk when the model asks for them. Pure C, one file per model family, no GPU required.
Thirteen engines run today. Ten are for language models: GLM-5.2/5.3 (which also runs Mistral-Large-4), GLM-5.3-Flash, Inkling, Kimi K3, DeepSeek V4 Flash, DeepSeek V4.1 Flash, MiMo-V2.6 Flash (and Pro), Qwen3.8-Flash-Next, Qwen3.6 (which also runs Qwen3-Coder, the dense Qwen3.8-27B, Flint, Muse Spark Open and LFM3-VL) and OLMoE. One draws pictures: Qwen-Image-2.1. Two answer decisions: Laya and GLiNER2.5-Decide,…
Description and README excerpt from JustVugg/colibri on GitHub ↗.
JustVugg/colibri was first seen on GitHub · Trending today on Nov 2, 2026. Since then it has appeared in 49 checks on 3 different days. Its best position was #4 of 13, reached on Nov 3, 11:00 UTC. It dropped off the list after Nov 4, 11:00 UTC.
Position on GitHub · Trending today at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by GitHub.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 4, 11:00 UTC, after 3 days of trending.
#4 on GitHub · Trending today, on Nov 3, 11:00 UTC. Trendoday checks this list every 60 minutes.
It was first seen on Nov 2, 2026 and has been on the list on 3 days (49 checks) since.
Mostly C; it is licensed under Apache-2.0. It has 46.1k stars and 5314 forks.