{"version":"v1","licence":"CC-BY-4.0","id":"colibri","name":"colibri","repo":"JustVugg/colibri","repository_url":"https://github.com/JustVugg/colibri","docs_url":"https://github.com/JustVugg/colibri#readme","description":"Runs huge mixture-of-experts AI models on an ordinary PC by reading parts of the model from disk; pure C, CPU-first, with a chat dashboard and local API.","summary":"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.","capabilities":["chat-assistant","local-models"],"tags":["Local LLM support","Runs AI locally","Mixture of experts","CLI","API","Windows","macOS","Linux","Works offline","GPU optional"],"alternatives":[{"product":"chatgpt-plus","jobs":["chat-assistant"],"coverage":"partial","note":"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."}],"facts":{"runs_locally":{"status":"yes","value":"Yes; models run on your own computer, with an optional local server for other apps","source_url":"https://github.com/JustVugg/colibri#readme","checked_at":"2026-11-03","confidence":"high","validation":"documentation_review","modes":["local","self-hosted"],"untrusted_source_quote":"colibri runs very large open models on the"},"code_license":{"status":"yes","value":"Apache 2.0","source_url":"https://github.com/JustVugg/colibri#license","checked_at":"2026-11-03","confidence":"high","validation":"documentation_review","spdx":"Apache-2.0","untrusted_source_quote":"Apache 2.0, Copyright 2026 Vincenzo Fornaro."},"model_license":{"status":"partial","value":"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","source_url":"https://github.com/JustVugg/colibri#license","checked_at":"2026-11-03","confidence":"medium","validation":"documentation_review","spdx":null,"applies":true,"untrusted_source_quote":"Each model keeps the licence its authors gave it (GLM-5.2 weights are released by Z.ai under MIT; Qwen-Image-2.1 is for non-commercial use only)."},"commercial_use":{"status":"partial","value":"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","source_url":"https://github.com/JustVugg/colibri#license","checked_at":"2026-11-03","confidence":"medium","validation":"documentation_review","untrusted_source_quote":"Each model keeps the licence its authors gave it (GLM-5.2 weights are released by Z.ai under MIT; Qwen-Image-2.1 is for non-commercial use only)."},"paid_services":{"status":"yes","value":"None required; the engine and the models it downloads are free","source_url":"https://github.com/JustVugg/colibri#readme","checked_at":"2026-11-03","confidence":"high","validation":"documentation_review","required":[],"optional":[],"untrusted_source_quote":"colibri is free and open source."},"hardware":{"status":"yes","value":"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","source_url":"https://github.com/JustVugg/colibri#get-started","checked_at":"2026-11-03","confidence":"high","validation":"documentation_review","cpu_ok":true,"min_vram_gb":null,"min_ram_gb":8,"untrusted_source_quote":"You need a computer with 8 GB of RAM at the very least"},"platforms":{"status":"yes","value":"Windows, macOS and Linux, with a one-step setup and prebuilt releases for each","source_url":"https://github.com/JustVugg/colibri#repo-layout","checked_at":"2026-11-03","confidence":"high","validation":"documentation_review","windows":"yes","macos":"yes","linux":"yes","untrusted_source_quote":"the one-step setup (Linux and macOS, Windows)"},"setup":{"status":"yes","value":"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","source_url":"https://github.com/JustVugg/colibri#get-started","checked_at":"2026-11-03","confidence":"high","validation":"documentation_review","level":"medium","untrusted_source_quote":"Double-click START-HERE.bat in the unzipped folder."}},"metrics":null,"url":"https://repoquarry.dev/projects/colibri","note":"Installation guidance: follow docs_url. This service never installs or runs code."}