JustVugg/colibri
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
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, 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, with a third decision model, Clef, on the Qwen3.6…
Read the full README ↗ · Preview checked 2026-10-31T18:56:24.399Z
Inside the original README — Document outline
- Get started in one step
- If something goes wrong
- Let your AI assistant set it up
- Or by hand
- What colibri is, and why
- Which model for my machine
- GPUs
- No GPU needed
- Vulkan: any GPU
- CUDA: NVIDIA cards
- Apple Silicon
- System One: a decision with a probability
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Repository facts
- Owner
- JustVugg
- Primary language
- C
- Stars
- 41,634
- Forks
- 4,601
- Open issues + pull requests
- 121
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-07-01T12:27:49.000Z
- Last push
- 2026-09-14T21:35:36.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-13T12:07:06.662Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.