Jan

Overview

Jan is an open-source ChatGPT alternative that runs 100% offline on your computer, offering complete privacy and control. It provides an intuitive desktop interface for interacting with large language models locally. Jan is powered by Cortex, a multi-engine platform supporting various architectures from PCs to multi-GPU clusters.

System Requirements

• CPU: 4+ cores recommended
• RAM: 8GB minimum, 16GB+ recommended
• GPU: Optional but recommended for better performance (NVIDIA GPU with 8GB+ VRAM ideal)
• Storage: 10GB+ (varies based on models downloaded)
• OS: Windows, macOS, or Linux

Installation Guide

Quick Installation (Recommended)

1. Visit the Jan website or GitHub releases page to download the latest installer for your operating system.

2. Run the downloaded installer and follow the installation prompts.

3. Launch Jan from your applications menu.

Docker Installation

For advanced users who prefer Docker:

1. Install Docker on your system if not already installed.

2. Pull and run the Jan container:

   docker run -d -p 3000:8080 --name jan-ai janhq/jan
   

3. Access Jan through your browser at http://localhost:3000

Practical Exercise: Getting Started with Jan

Now that you have Jan installed, let’s walk through a simple exercise to help you get familiar with the basics.

Step 1: Download a Model

1. Open Jan and navigate to the Model Hub.
2. Browse available models like Llama3, Gemma, or Mistral.
3. Select a model that matches your hardware capabilities (smaller models for systems with limited resources).
4. Click “Download” and wait for the model to download and install.

Step 2: Create Your First Chat

1. Once your model is downloaded, create a new chat session.
2. Select your downloaded model from the dropdown menu.
3. Type a prompt in the chat input field, such as “Explain how neural networks work in simple terms.”
4. Press Enter and observe the model’s response.
5. Try adjusting parameters like temperature and max tokens in the settings panel to see how they affect responses.

Step 3: Exploring Advanced Features

Once you’re comfortable with the basics, explore some of Jan’s advanced features:

• Use the OpenAI-equivalent API at https://localhost:1337 to connect Jan with other applications
• Try using multiple models in the same chat session to compare outputs
• Import your own GGUF model files for specialized use cases
• Connect to cloud model services like OpenAI or Anthropic through Jan’s interface
• Create custom chat templates for specific use cases

Resources

Official Documentation

The official documentation is the best place to find detailed information about Jan.

Read the Documentation

Community Support

Join the community to get help, share your experiences, and contribute to the project.

Discord Community

GitHub Repository

Explore the source code, report issues, or contribute to the project.

Jan on GitHub