# Colibri

> Run large MoE models on everyday hardware

A pure C engine that streams expert weights from disk to run big mixture-of-experts models on modest machines.

- Source: https://github.com/JustVugg/colibri
- Homepage: https://justvugg.github.io/colibri
- License: Apache-2.0
- Language: C
- Stars: 39579
- Forks: 4334
- Contributors: 176
- Last commit: 2026-09-24
- Latest release: v1.12.1 (2026-09-24)
- Purpose: AI & LLM tooling, Local inference
- Runs on: CLI
- For: Personal

## Worth score: 79/100

How much DigGitHub recommends it, from activity, adoption, docs, license and security signals.

- Popularity: 23/25
- Momentum: 10/20
- Maintenance: 25/25
- Community: 13/15
- Readiness: 8/15

## Alternatives

- [Ollama](https://diggithub.com/ollama/ollama.md): Run open-weight LLMs locally with one command
- [llama.cpp](https://diggithub.com/ggml-org/llama.cpp.md): LLM inference in C/C++ on CPUs and GPUs
- [llmfit](https://diggithub.com/AlexsJones/llmfit.md): Find which LLMs run on your hardware
- [llamafile](https://diggithub.com/mozilla-ai/llamafile.md): Run an LLM from a single file
- [exo](https://diggithub.com/exo-explore/exo.md): Run frontier AI models across your own devices
- [ds4](https://diggithub.com/antirez/ds4.md): Local DeepSeek 4 inference engine

---

Source page: https://diggithub.com/JustVugg/colibri
Updated: 2026-10-05