Jan janhq/jan

Desktop app that downloads and runs LLMs from Hugging Face offline, with optional cloud model connections and a local OpenAI-compatible API.

Creator kit + Compare GitHub ↗ Install guide (official) ↗

Jan at a glance

Checked 15 Oct 2026

Jan is a desktop chat app (Tauri, bundled llama.cpp engine) that downloads open models such as Llama, Gemma, Qwen and gpt-oss from Hugging Face and runs them offline, or connects to OpenAI, Anthropic, Mistral and Groq. It also serves a local OpenAI-compatible API on port 1337. Installers for Windows, macOS and Linux. Code is Apache-2.0; it ships no weights, so each model's licence matters. The README suggests 8GB RAM for 3B models, 16GB for 7B and 32GB for 13B on macOS.

Cite this pageRepoQuarry. “Jan.” Checked 15 Oct 2026. https://repoquarry.dev/projects/jan

How much of ChatGPT Plus does it replace?

1 of 3 jobs. Replaces the chat interface; answer quality depends on the model you run. Local models are generally less capable than paid frontier models.

Chat assistant Partial replacement

Chat with your documents Not covered

Web search answers Not covered

For chat with your documents, web search answers, see other ChatGPT Plus alternatives. You may also need to build an interface, an API server and hosting yourself.

Facts, with sources

Every answer links to where we found it. We read the documentation; we did not install it.

Report a correction

QuestionAnswerSourceChecked

Runs on my machine? Yes, desktop app running models offline Download and run LLMs with full control and privacy. github.com · jan#readme ↗ 1d ago

Code licence Apache-2.0 (attribution requested) Licensed under the Apache License, Version 2.0 ... Attribution is requested in user-facing documentation and materials, where appropriate. github.com · LICENSE ↗ 1d ago

Model weights licence No bundled weights; licence depends on the model you download Download and run LLMs (Llama, Gemma, Qwen, GPT-oss etc.) from HuggingFace github.com · jan#features ↗ 1d ago

Commercial use Yes, Apache-2.0 app; check the licence of the model you use github.com · LICENSE ↗ 1d ago

Paid services needed? None required; cloud model providers optional Privacy First: Everything runs locally when you want it to github.com · jan#features ↗ 1d ago

Hardware macOS 8GB RAM for 3B, 16GB for 7B, 32GB for 13B models; GPU optional macOS: 13.6+ (8GB RAM for 3B models, 16GB for 7B, 32GB for 13B) github.com · jan#system-requirements ↗ 1d ago

Operating systems Windows 10+, macOS 13.6+, Linux (deb, AppImage, Flathub) Windows: 10+ with GPU support for NVIDIA/AMD/Intel Arc github.com · jan#installation ↗ 1d ago

Setup effort Easy; download installer (exe, dmg, deb, AppImage) or app stores The easiest way to get started is by downloading one of the following versions for your respective operating system github.com · jan#installation ↗ 1d ago