LibreAI / LLM locaux / colibri
// local-llm · JustVugg/colibri

colibri

colibri est un projet de LLM locaux open source, créé par JustVugg (JustVugg/colibri sur GitHub). Il compte 49 279 étoiles sur GitHub et 5 777 forks, il est publié sous la licence Apache-2.0 et a été mis à jour pour la dernière fois sur GitHub le 31 octobre 2026.

Tiny C engine that runs huge MoE models on the machine you already own — GLM, Kimi K3, DeepSeek, Qwen, Apache-2.0

★ 49,3 k étoiles⑂ 5,8 k forksApache-2.0mis à jour oct. 2026
▦ visuel — le README de ce projet ne contient aucune capture intégrable,
voici donc un emplacement réservé. Le guide ci-dessous est complet malgré tout.
// détails du projet

Détails du projet

Étoiles GitHub
49 279
Forks
5 777
Licence
Apache-2.0
Dernière mise à jour sur GitHub
31 octobre 2026
Catégorie
LLM locaux
Type de fiche
Guide d'installation complet
Site officiel
Official site
// fonctionnement

Comment ça marche

  1. Check the machine

    You need 8 GB of RAM at minimum (16 GB or more is better), 22 GB free on disk for the smallest model, and an internet connection. A graphics card is optional.

  2. Run the one-step setup

    Clone the repo and run the setup script (START-HERE.bat on Windows). It checks your hardware, recommends a model, builds the engine, downloads the model and starts the dashboard.

  3. Chat or connect apps

    Use ./coli chat in the terminal, the browser dashboard, or point any OpenAI-compatible app at the local server on port 8000.

// fonctionnalités

Pourquoi on l'adore

744B-parameter models on ordinary hardware

Hot experts on GPU, warm ones in RAM, cold ones streamed from NVMe — placement, not brute-force memory.

No GPU required

Runs on CPU, on any GPU through Vulkan, and on NVIDIA cards through CUDA.

Thirteen engines

Chat, coding, vision and image models plus decision models, from GLM and Kimi K3 to DeepSeek and Qwen.

OpenAI and Anthropic compatible APIs

Other apps talk to colibri over standard endpoints.

A dashboard that shows the work

Watch every expert fire as the model answers.

MCP server included

coli mcp lets AI assistants detect hardware, recommend models and manage colibri.

// lancez-le

Lancez-le vous-même

  1. Step 1 — Clone the repo

    Download the source and move into the project folder.

    git clone https://github.com/JustVugg/colibri
  2. Step 2 — Run the setup

    From the colibri folder, run the one-step setup: it checks your machine, recommends a model and starts colibri.

    cd colibri && ./start-here.sh
  3. Step 3 — Chat

    Talk to the model in the terminal.

    ./coli chat
// cas d'usage

Ce que vous pouvez créer

  • Run frontier open MoE models without a datacenter GPU
  • Chat with GLM, Kimi K3, DeepSeek and Qwen locally
  • Serve models to other apps over an OpenAI-compatible API
  • Study MoE inference on an open research platform

For comparison, the same shelf also holds atomic-agent — is a local-first AI agent and FreeToken — Run 290B+ frontier MoE models on your own gaming PC. The complete list is the Local LLM shelf. Before running a model locally, check how much VRAM you need for local LLMs — model size has to match your hardware.

// faq

Questions fréquentes

Do I need a GPU?

No — colibri runs on CPU. Vulkan (any GPU) or CUDA (NVIDIA) speed it up, and the setup picks the fastest build for your machine.

How much RAM and disk do I need?

8 GB of RAM at minimum, 16 GB or more is better; 22 GB disk for the smallest model.

Which models can it run?

GLM-5.2/5.3, Kimi K3, DeepSeek V4/V4.1 Flash, MiMo-V2.6, Qwen3.6/3.8, OLMoE, plus Qwen-Image-2.1 and decision models — thirteen engines.

Is it really free?

Yes — Apache 2.0. You download the model weights from Hugging Face; the engine itself costs nothing.

What is the dashboard?

A browser UI on port 8000 with chat, plus OpenAI- and Anthropic-compatible API endpoints for other apps.

// continuez l'exploration

Outils similaires

LLM locaux

atomic-agent

Atomic Agent is a local-first AI agent. Runs open-weight models on your own machine via llama.cpp.

★ 2,7 k étoilesMIT
Voir le guide →
LLM locaux

FreeToken

Run 290B+ frontier MoE models on your own gaming PC at interactive speed

★ 17,2 k étoilesApache-2.0
Voir le guide →
LLM locaux

Ollama

The simplest way to run open language models on your own machine.

★ 182,1 k étoilesMIT
Voir le guide →
LLM locaux

DeepSeek-Coder-V2

DeepSeek-Coder-V2 — DeepSeek's open code model family that challenged closed-source code models.

★ 7,0 k étoilesMIT
Voir le guide →
LLM locaux

GPT-OSS

GPT-OSS — OpenAI open-weight language models: gpt-oss-120b for production reasoning and gpt-oss-20b for local use, Apache-2.0

★ 20,5 k étoilesApache-2.0
Voir le guide →
LLM locaux

maid

Maid is a free and open source application for interfacing with llama.cpp models locally, and with Anthropic, DeepSeek, Ollama, Mistral and OpenAI models rem…

★ 2,7 k étoilesMIT
Voir le guide →
// alternatives

Alternatives en LLM locaux

Les autres projets de la catégorie LLM locaux avec le plus d'étoiles du catalogue LibreAI — la sélection réaliste d'alternatives si colibri ne vous convient pas.

  • Ollama★ 182,1 k

    The simplest way to run open language models on your own machine.

  • Open Webui★ 153,9 k

    User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

  • llama.cpp★ 130,2 k

    LLM inference in C/C++

  • vLLM★ 93,1 k

    A high-throughput and memory-efficient inference and serving engine for LLMs

  • lobehub★ 83,0 k

    🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

// plus en local-llm

Plus en LLM locaux

Projets de la catégorie LLM locaux proches dans le catalogue, les plus proches en étoiles de colibri — continuez à explorer de part et d'autre.

  • litellm★ 60,1 k

    The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, an…

  • exo★ 47,7 k

    Run frontier AI locally.

  • Unsloth★ 77,2 k

    Run and fine-tune LLMs and diffusion models locally — faster training, smaller memory footprint.

  • Text Generation Webui★ 47,7 k

    Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private

  • GPT4All★ 77,4 k

    GPT4All — run local LLMs on any device: a free desktop chat client and Python SDK that run open models entirely on your CPU, no GPU or cloud required

  • Jan★ 44,8 k

    Jan is an open source alternative to ChatGPT that runs 100% offline on your computer

Obtenir colibri

Gratuit et ouvert : récupérez le code source, mettez une étoile au dépôt et commencez à créer.