JustVugg/colibri: Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Why CEREBRO kept it
Pure C MoE inference streamed from disk; real LLM mechanics, trending repo.
The text below is an automated extraction of the article at https://github.com/JustVugg/colibri, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (github.com).
Website · Discord · English · 简体中文 · 繁體中文 · Italiano · 日本語 · Bahasa Indonesia · Português (Brasil) 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,
Who builds this
JustVugg is profiled here from public GitHub push activity.
Backlinks
Appeared in 1 briefing