Jan at a glance
Jan is an AI apis & infrastructure tool. Run LLMs like Mistral or Llama2 locally and offline on your computer, or connect to remote AI APIs.…
- Best for:
- Open-source project (MIT license) hosted on GitHub under janhq/jan
- Pricing:
- Open Source
- Standout feature:
- Run large language models fully locally on-device
- Main limitation:
- Performance is hardware-dependent — large models are slow or unusable on low-RAM machines
About Jan
Jan is a free, open-source desktop application that lets users run large language models (LLMs) entirely on their own hardware, with no data sent to external servers. It provides a clean chat interface and a built-in model hub for downloading GGUF-format models (Llama, Mistral, Phi, Gemma, and more). Jan also runs a local OpenAI-compatible API server, making it a drop-in local backend for any app built against the OpenAI SDK. It supports GPU acceleration on NVIDIA and Apple Silicon hardware. Targeted at developers, privacy-conscious users, and AI enthusiasts who want full control over their AI stack without recurring cloud costs or data exposure.
Key Features of Jan
Here's what Jan actually does — the capabilities our editorial team and AI research surfaced from the product, documentation, and user reports:
