LibreAI / Lokale LLMs / colibri
// local-llm · JustVugg/colibri

colibri

colibri ist ein Open-Source-Projekt aus der Kategorie Lokale LLMs von JustVugg (JustVugg/colibri auf GitHub). Es hat 49.279 Sterne auf GitHub und 5.777 Forks, wird unter der Lizenz Apache-2.0 veröffentlicht und wurde zuletzt am 31. Oktober 2026 auf GitHub aktualisiert.

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

★ 49,3 Tsd. Sterne⑂ 5,8 Tsd. ForksApache-2.0aktualisiert Okt 2026
▦ Visual — das README dieses Projekts enthält keinen einbettbaren Screenshot,
darum hier ein Platzhalter. Die Anleitung unten ist trotzdem vollständig.
// projektdaten

Projektdaten

GitHub-Sterne
49.279
Forks
5.777
Lizenz
Apache-2.0
Zuletzt auf GitHub aktualisiert
31. Oktober 2026
Kategorie
Lokale LLMs
Eintragstyp
Vollständige Installationsanleitung
Offizielle Website
Official site
// so funktioniert es

So funktioniert es

  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.

// funktionen

Warum es so beliebt ist

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.

// selbst ausführen

Führe es selbst aus

  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
// anwendungsfälle

Was du damit bauen kannst

  • 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.

// häufige fragen

Häufige Fragen

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.

// weiter entdecken

Ähnliche Tools

Lokale LLMs

atomic-agent

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

★ 2,7 Tsd. SterneMIT
Anleitung ansehen →
Lokale LLMs

FreeToken

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

★ 17,2 Tsd. SterneApache-2.0
Anleitung ansehen →
Lokale LLMs

Ollama

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

★ 182,1 Tsd. SterneMIT
Anleitung ansehen →
Lokale LLMs

DeepSeek-Coder-V2

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

★ 7,0 Tsd. SterneMIT
Anleitung ansehen →
Lokale LLMs

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 Tsd. SterneApache-2.0
Anleitung ansehen →
Lokale LLMs

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 Tsd. SterneMIT
Anleitung ansehen →
// alternativen

Alternativen im Bereich Lokale LLMs

Die anderen Projekte der Kategorie Lokale LLMs mit den meisten Sternen im LibreAI-Katalog — die realistische Auswahl, falls colibri nicht das Richtige ist.

  • Ollama★ 182,1 Tsd.

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

  • Open Webui★ 153,9 Tsd.

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

  • llama.cpp★ 130,2 Tsd.

    LLM inference in C/C++

  • vLLM★ 93,1 Tsd.

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

  • lobehub★ 83,0 Tsd.

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

// mehr in local-llm

Mehr in Lokale LLMs

Verwandte Projekte der Kategorie Lokale LLMs im Katalog, die colibri bei den Sternen am nächsten stehen — zum Weiterstöbern auf beiden Seiten.

  • litellm★ 60,1 Tsd.

    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 Tsd.

    Run frontier AI locally.

  • Unsloth★ 77,2 Tsd.

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

  • Text Generation Webui★ 47,7 Tsd.

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

  • GPT4All★ 77,4 Tsd.

    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 Tsd.

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

Hol dir colibri

Kostenlos und offen — hol dir den Quellcode, gib dem Repository einen Stern und leg los.