# colibri > colibri (v2.1.0, 31 Oct 2026, ~47k stars) is a pure-C engine that runs large open models such as Qwen3.6, DeepSeek V4 Flash and GLM-5.2 on your own machine, keeping the active part in RAM and streaming the rest from disk. It gives a terminal chat, a browser dashboard and OpenAI- and Anthropic-compatible local APIs. Apache 2.0; each model keeps its own licence. Needs at least 8 GB of RAM and 22 GB of disk for the smallest model. Small models reach about 6-14 tokens a second on a CPU; the giant ones often run at 1 token a second or slower without big hardware. - Repository: https://github.com/JustVugg/colibri - Official docs: https://github.com/JustVugg/colibri#readme - Checked: 2026-11-03 ## What it replaces - ChatGPT Plus: Chat assistant (partial). Local chat with open models, private and free once downloaded. The models that fit in ordinary RAM run at about 6 to 14 tokens a second on a CPU; the big ones that stream from disk often manage 1 a second or less unless you have lots of RAM or a GPU. Downloads run from 19 GB to over 1 TB, the big models are heavily compressed, and there is no phone app or cloud sync. Answer quality depends on the model you pick. - Use it instead of paying for ChatGPT Plus? Personal use: Yes. Business: Partly (Commercial use with conditions: The engine is Apache 2.0, so yes; most chat models allow it, but Qwen-Image-2.1 does not…; Model weights: Depends on the model. The README says GLM-5.2 is MIT and Qwen-Image-2.1 is non-commercial…). ## Facts, with sources | Question | Status | Answer | Source | Checked | |---|---|---|---|---| | Runs on my machine? | Confirmed | Yes; models run on your own computer, with an optional local server for other apps | https://github.com/JustVugg/colibri#readme | 2026-11-03 | | Code licence | Confirmed | Apache 2.0 | https://github.com/JustVugg/colibri#license | 2026-11-03 | | Model weights licence | Partial | Depends on the model. The README says GLM-5.2 is MIT and Qwen-Image-2.1 is non-commercial only. On Hugging Face the default small model Qwen3.6-35B-A3B is Apache 2.0, DeepSeek V4 Flash and MiMo-V2.6 Flash are MIT, and Kimi K3 and Qwen3.8-Flash-Next use custom licences; Muse Spark Open uses Meta's licence agreement | https://github.com/JustVugg/colibri#license | 2026-11-03 | | Commercial use | Partial | The engine is Apache 2.0, so yes; most chat models allow it, but Qwen-Image-2.1 does not and some models have custom terms to check | https://github.com/JustVugg/colibri#license | 2026-11-03 | | Paid services needed? | Confirmed | None required; the engine and the models it downloads are free | https://github.com/JustVugg/colibri#readme | 2026-11-03 | | Hardware | Confirmed | At least 8 GB of RAM (16 GB or more is better) and 22 GB free disk for the smallest model; no GPU needed. Big models need 16-128 GB of RAM and a fast SSD | https://github.com/JustVugg/colibri#get-started | 2026-11-03 | | Operating systems | Confirmed | Windows, macOS and Linux, with a one-step setup and prebuilt releases for each | https://github.com/JustVugg/colibri#repo-layout | 2026-11-03 | | Setup effort | Confirmed | Medium; a setup script picks and downloads a model for you (double-click on Windows, a few terminal commands on macOS and Linux), but downloads are large | https://github.com/JustVugg/colibri#get-started | 2026-11-03 | ## Alternatives to colibri - [Ollama](https://repoquarry.dev/projects/ollama.md): Local model runner that downloads and serves open LLMs (Gemma, Qwen, DeepSeek, gpt-oss and more) with a CLI and local API. - [Jan](https://repoquarry.dev/projects/jan.md): Desktop app that downloads and runs LLMs from Hugging Face offline, with optional cloud model connections and a local OpenAI-compatible API. - [Open WebUI](https://repoquarry.dev/projects/open-webui.md): Self-hosted AI chat platform for Ollama and OpenAI-compatible APIs, with RAG over your files, web search and multi-user admin. - [Odysseus](https://repoquarry.dev/projects/odysseus.md): Self-hosted AI workspace with chat, agents, deep research, documents, email, notes and calendar, using local models or your own API keys. - [LobeHub (formerly LobeChat)](https://repoquarry.dev/projects/lobehub.md): Self-hostable AI chat and agent workspace (formerly LobeChat) with multi-provider models, plugins and a desktop app. - [AnythingLLM](https://repoquarry.dev/projects/anything-llm.md): All-in-one desktop or Docker app to chat with your documents using local or cloud LLMs, with agents and a built-in vector database. --- Source: RepoQuarry (https://repoquarry.dev/projects/colibri). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.