Jan

Jan (Jan.ai) is a free and open-source tool for running large models locally and conducting AI chat conversations. It can assist users in installing, deploying, running, and using open-source versions of ChatGPT alternative large models, such as LLaMa, Mistral, Phi-2, and more than 20 other models on their local computers (Windows, Mac, Linux). It also supports entering one’s own OpenAI API Key to run GPT. Compared with Ollama, which was previously introduced in AI toolsets, this tool provides a conversation UI and an API server, making it suitable for developers, researchers, or AI enthusiasts to locally experience open-source large models.

The main features of Jan

• Run Open-Source Large Models Locally: Supports more than 20 models such as LlaMa, Mistral, Phi-2, DeepSeek, Yi, etc. Models can be manually imported or downloaded from the model library.
• Simple and User-Friendly Chat Interface: The software interface is clean, simple, intuitive, and easy to use. You can directly have a quick conversation with open-source large models locally.
• Support Multiple Platforms: Jan can run on operating systems such as Windows, Mac (Intel, M1/M2/M3), and Linux. A mobile APP will be launched subsequently.
• Built-in API Server: Compatible with OpenAI API. You can obtain model information, download, start, stop models, and chat through the API.