Jan

Jan (Jan.ai) is a free and open-source tool for running large AI models locally and engaging in AI chat dialogues. It helps users install, deploy, run, and use open-source versions of ChatGPT on their local computers (Windows, Mac, Linux) to replace large models such as LLaMa, Mistral, Phi-2, and over 20 others. It also supports entering your own OpenAI API Key to run GPT. Compared to Ollama , which was previously introduced in the AI ​​toolset, this tool provides a conversational UI and API server, making it suitable for developers, researchers, or AI enthusiasts to experience large open-source models locally.

Jan’s main functions

• Run large open-source models locally : Supports more than 20 models including LlaMa, Mistral, Phi-2, DeepSeek, and Yi. Models can be imported manually or downloaded from the model library.
• Simple and easy-to-use chat interface : The software interface is clean, simple, intuitive and easy to use, allowing for quick and direct local chat with open-source large models.
• Supports multiple platforms : Jan supports running on operating systems such as Windows, Mac (Intel, M1/M2/M3) and Linux, and a mobile app will be launched later.
• Built-in API server : Compatible with the OpenAI API, allowing users to obtain model information, download, start, stop models, and chat via the API.

How to use Jan

1. Visit Jan’s official website (jan.ai), select the version corresponding to your computer’s operating system, and click Download to download.
2. Then install and open the software, and click “Download your first model” in the lower left corner of the software interface.
3. Enter the model library Hub interface, select the model you are interested in to download, and click “Use” to use the model after the download is complete.
4. Simply enter your description in the dialogue interface to interact with the model you selected.

Jan is still under development and will support mobile apps, AI assistant creation, inference engines, plugin extensions, and other features in the future.