Documentation
Start Chatting

Start Chatting

Step 1: Install Jan

  1. Download Jan
  2. Install the app (Mac, Windows, Linux)
  3. Launch Jan

Step 2: Download a Model

Jan requires a model to chat. Download one from the Hub:

  1. Go to the Hub Tab
  2. Browse available models (must be GGUF format)
  3. Select one matching your hardware specs
  4. Click Download

Download a Model

⚠️

Models consume memory and processing power. Choose based on your hardware specs.

HuggingFace models: Some require an access token. Add yours in Settings > Model Providers > Llama.cpp > Hugging Face Access Token.

Add HF Token

Step 3: Enable GPU Acceleration (Optional)

For Windows/Linux with compatible graphics cards:

  1. Go to () Settings > Hardware
  2. Toggle GPUs to ON

Turn on GPU acceleration

Install required drivers before enabling GPU acceleration. See setup guides for Windows & Linux.

Step 4: Start Chatting

  1. Click New Chat () icon
  2. Select your model in the input field dropdown
  3. Type your message and start chatting

Create New Thread

Managing Conversations

Jan organizes conversations into threads for easy tracking and revisiting.

View Chat History

  • Left sidebar shows all conversations
  • Click any chat to open the full conversation
  • Favorites: Pin important threads for quick access
  • Recents: Access recently used threads

Favorites and Recents

Edit Chat Titles

  1. Hover over a conversation in the sidebar
  2. Click three dots () icon
  3. Click Rename
  4. Enter new title and save

Context Menu

Delete Threads

⚠️

Thread deletion is permanent. No undo available.

Single thread:

  1. Hover over thread in sidebar
  2. Click three dots () icon
  3. Click Delete

All threads:

  1. Hover over Recents category
  2. Click three dots () icon
  3. Select Delete All

Advanced Features

Custom Assistant Instructions

Customize how models respond:

  1. Use the assistant dropdown in the input field
  2. Or go to the Assistant tab to create custom instructions
  3. Instructions work across all models

Assistant Instruction

Add an Assistant Instruction

Model Parameters

Fine-tune model behavior:

  • Click the Gear icon next to your model
  • Adjust parameters in Assistant Settings
  • Switch models via the model selector

Chat with a Model

Connect Cloud Models (Optional)

Connect to OpenAI, Anthropic, Groq, Mistral, and others:

  1. Open any thread
  2. Select a cloud model from the dropdown
  3. Click the Gear icon beside the provider
  4. Add your API key (ensure sufficient credits)

Connect Remote APIs

For detailed setup, see Remote APIs.

LinuxJan Nano 32k