> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/janhq/jan/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Get from zero to your first AI chat in under 5 minutes. Download Jan, install a model, and start chatting.

# Quickstart

Get up and running with Jan in minutes. This guide takes you from installation to your first AI conversation with a local model.

<Steps>
  <Step title="Install Jan">
    Download Jan for your platform and install it.

    <Tabs items={["Windows", "macOS", "Linux"]}>
      <Tab>
        1. Download [jan.exe](https://app.jan.ai/download/latest/win-x64)
        2. Run the installer
        3. Wait for installation to complete
        4. Launch Jan

        <Info>
          Windows 10 or higher required. GPU acceleration available for NVIDIA, AMD, and Intel Arc GPUs.
        </Info>
      </Tab>

      <Tab>
        1. Download [jan.dmg](https://app.jan.ai/download/latest/mac-universal)
        2. Open the DMG file
        3. Drag Jan to your Applications folder
        4. Launch Jan from Applications

        <Info>
          macOS 13.6+ required. Apple Silicon Macs (M1/M2/M3) get automatic Metal acceleration for better performance.
        </Info>
      </Tab>

      <Tab>
        **Ubuntu/Debian:**

        ```bash theme={null}
        # Download the .deb package
        wget https://app.jan.ai/download/latest/linux-amd64-deb

        # Install
        sudo dpkg -i jan-linux-amd64-*.deb
        ```

        **Other distributions (AppImage):**

        ```bash theme={null}
        # Download AppImage
        wget https://app.jan.ai/download/latest/linux-amd64-appimage

        # Make executable and run
        chmod +x jan-linux-x86_64-*.AppImage
        ./jan-linux-x86_64-*.AppImage
        ```

        <Info>
          Most Linux distributions supported. GPU acceleration available for NVIDIA (CUDA), AMD (Vulkan), and Intel Arc (Vulkan).
        </Info>
      </Tab>
    </Tabs>

    **Alternative Download Options:**

    * Official website: [jan.ai/download](https://jan.ai/download)
    * GitHub releases: [github.com/janhq/jan/releases](https://github.com/janhq/jan/releases)
    * Microsoft Store (Windows)
    * Flathub (Linux)
  </Step>

  <Step title="Download Your First Model">
    We recommend starting with **Jan v1**, a 4B parameter model optimized for reasoning and tool calling.

    1. Open Jan
    2. Navigate to the **Hub** tab in the left sidebar
    3. Search for **"Jan v1"**
    4. Choose a quantization based on your available RAM:
       * **Q4\_K\_M** (2.5 GB) - Good balance for most users
       * **Q8\_0** (4.28 GB) - Best quality if you have 16GB+ RAM
    5. Click **Download**
    6. Wait for the download to complete

    <Note>
      Jan v1 achieves 91.1% accuracy on SimpleQA and excels at tool calling, making it perfect for web search and reasoning tasks.
    </Note>

    **Other Popular Models:**

    * **Llama 3.2 3B** - Fast, general-purpose model (2GB)
    * **Gemma 2 2B** - Google's efficient model (1.6GB)
    * **Qwen 2.5 7B** - Excellent for coding and reasoning (4.5GB)
    * **DeepSeek R1** - Advanced reasoning model (8GB+)
  </Step>

  <Step title="Start Your First Chat">
    Once your model is downloaded, you're ready to chat!

    1. Click the **New Chat** button (pencil icon) in the top-left
    2. In the input field at the bottom, click the model dropdown
    3. Select **Jan v1** (or your chosen model)
    4. Type your first message and press Enter

    **Try these prompts:**

    ```
    Explain quantum computing in simple terms
    ```

    ```
    Help me write a Python function to sort a list
    ```

    ```
    What are the pros and cons of electric vehicles?
    ```

    <Tip>
      The first response may take a moment as the model loads into memory. Subsequent responses will be faster.
    </Tip>
  </Step>
</Steps>

## What's Next?

You're now chatting with AI completely offline! Here are some powerful features to explore:

### Enable Web Search (MCP)

Give Jan v1 access to current web information with real-time search:

1. Go to **Settings** → **MCP**
2. Add the Serper MCP server (includes 2,500 free searches)
3. Enable tools in your chat
4. Ask Jan to search the web for current information

<Card title="Serper MCP Tutorial" icon="magnifying-glass" href="https://jan.ai/docs/desktop/mcp-examples/search/serper">
  Complete guide to enabling web search in Jan with 2,500 free searches per month.
</Card>

### Manage Your Conversations

Jan organizes all your chats into threads for easy management:

**View Chat History:**

* Left sidebar shows all conversations
* **Favorites**: Pin important threads by clicking the star icon
* **Recents**: Quick access to recently used threads

**Rename Conversations:**

1. Hover over a conversation in the sidebar
2. Click the three dots (...) menu
3. Select "Rename"
4. Enter a descriptive title

**Delete Threads:**

1. Hover over a thread
2. Click three dots (...)
3. Select "Delete"

<Warning>
  Thread deletion is permanent with no undo option. Make sure you want to delete before confirming.
</Warning>

### Create Custom Assistants

Customize how models respond to match your workflow:

1. Click the **Assistant** tab in the left sidebar
2. Click **Create New Assistant**
3. Give it a name (e.g., "Code Reviewer", "Writing Assistant")
4. Add custom instructions:
   ```
   You are a senior software engineer specializing in Python.
   Always include code examples and best practices.
   Format code blocks with proper syntax highlighting.
   ```
5. Save and select your assistant in any chat

<Info>
  Assistant instructions work across all models, so you can switch models while keeping the same personality and behavior.
</Info>

### Adjust Model Parameters

Fine-tune model behavior for different tasks:

1. In any chat, click the **Gear icon** next to the model name
2. Adjust these key parameters:
   * **Temperature** (0.0-1.0): Lower = more focused, higher = more creative
   * **Max Tokens**: Maximum length of responses
   * **Top P**: Controls diversity of word selection
   * **Frequency Penalty**: Reduces repetition

**Recommended Settings:**

* **Creative Writing**: Temperature 0.8-1.0
* **Code Generation**: Temperature 0.2-0.4
* **Factual Q\&A**: Temperature 0.1-0.3
* **General Chat**: Temperature 0.7 (default)

### Download More Models

Explore thousands of models from HuggingFace:

1. Go to the **Hub** tab
2. Browse by category or search for specific models
3. Popular categories:
   * **General Chat**: Llama, Gemma, Mistral
   * **Coding**: Qwen Coder, DeepSeek Coder
   * **Reasoning**: DeepSeek R1, Jan v1
   * **Small & Fast**: Phi-3, TinyLlama

<Note>
  **Memory Requirements:**

  * 8GB RAM → up to 3B parameter models
  * 16GB RAM → up to 7B parameter models
  * 32GB RAM → up to 13B parameter models

  With GPU acceleration, you can run larger models with less system RAM.
</Note>

### Connect Cloud Models (Optional)

Combine local and cloud AI in one interface:

1. Open any chat
2. Click the model dropdown
3. Select a cloud provider (OpenAI, Anthropic, Groq, Mistral)
4. Click the **Gear icon** next to the provider name
5. Enter your API key
6. Start chatting with GPT-4, Claude, or other cloud models

**Supported Cloud Providers:**

* **OpenAI**: GPT-4, GPT-4 Turbo, GPT-3.5
* **Anthropic**: Claude 3.5 Sonnet, Claude 3 Opus/Haiku
* **Groq**: Ultra-fast inference with Llama, Mixtral
* **Mistral AI**: Mistral Large, Medium, Small
* **Cohere**: Command R+, Command R
* **Google**: Gemini Pro, Gemini Flash

<Card title="Remote Models Guide" icon="cloud" href="https://jan.ai/docs/desktop/remote-models/openai">
  Detailed setup instructions for connecting cloud AI providers.
</Card>

### Use the Local API Server

Jan runs an OpenAI-compatible API server at `localhost:1337`:

```bash theme={null}
# Example: Chat completion
curl http://localhost:1337/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "jan-v1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
```

Use this to integrate Jan with:

* Continue.dev (VS Code AI coding assistant)
* Tabby (AI code completion)
* n8n (workflow automation)
* LLMCord (Discord bot)
* Custom applications

<Card title="API Server Examples" icon="code" href="https://jan.ai/docs/desktop/server-examples/continue-dev">
  See real-world examples of integrating Jan's API with popular tools.
</Card>

## Troubleshooting

### Model Won't Load

* **Check RAM**: Ensure you have enough memory for the model size
* **GPU Settings**: Go to Settings → Hardware → GPUs to enable/disable GPU acceleration
* **Restart Jan**: Sometimes a fresh start helps

### Slow Performance

* **Enable GPU acceleration** (Settings → Hardware)
* **Use smaller models** (3B-7B instead of 13B+)
* **Lower quantization** (Q4 instead of Q8)
* **Close other applications** to free up RAM

### Download Issues

* **Check internet connection**
* **Verify disk space** (10GB+ free recommended)
* **Try different mirror**: Some models have multiple download sources
* **Resume failed downloads**: Jan automatically resumes interrupted downloads

### GPU Not Detected

<Tabs items={["NVIDIA", "AMD/Intel Arc", "Apple Silicon"]}>
  <Tab>
    1. Install [NVIDIA drivers](https://www.nvidia.com/en-us/drivers/) (version 470.63.01+)
    2. Install [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads) (version 11.7+)
    3. Verify installation:
       ```bash theme={null}
       nvidia-smi
       nvcc --version
       ```
    4. Enable in Jan: Settings → Hardware → GPUs → Toggle ON
  </Tab>

  <Tab>
    1. Ensure Vulkan support is installed (usually included with GPU drivers)
    2. Enable in Jan: Settings → Hardware → GPUs → Toggle ON
    3. Select Vulkan backend: Settings → Local Engine → Llama.cpp → Backend → Vulkan
  </Tab>

  <Tab>
    Metal acceleration is automatic on Apple Silicon Macs (M1/M2/M3). No configuration needed.

    Intel-based Macs run on CPU only without GPU acceleration.
  </Tab>
</Tabs>

<Card title="Full Troubleshooting Guide" icon="life-ring" href="https://jan.ai/docs/desktop/troubleshooting">
  Comprehensive troubleshooting documentation for common issues.
</Card>

## Getting Help

If you run into issues:

1. Check the [troubleshooting docs](https://jan.ai/docs/desktop/troubleshooting)
2. Search [GitHub issues](https://github.com/janhq/jan/issues)
3. Ask in [Discord #🆘|jan-help](https://discord.gg/FTk2MvZwJH) channel
4. Include:
   * Your OS and version
   * Jan version (Help → About)
   * Error messages or logs
   * Steps to reproduce

## Next Steps

<CardGroup cols={2}>
  <Card title="Installation Guide" icon="gear" href="/installation">
    Platform-specific installation details and GPU setup instructions.
  </Card>

  <Card title="Model Parameters" icon="sliders" href="https://jan.ai/docs/desktop/model-parameters">
    Learn how to fine-tune model behavior for different use cases.
  </Card>

  <Card title="MCP Integration" icon="puzzle" href="https://jan.ai/docs/desktop/mcp">
    Enable agentic capabilities with web search, tools, and integrations.
  </Card>

  <Card title="API Reference" icon="code" href="https://jan.ai/api-reference">
    Complete API documentation for building integrations.
  </Card>
</CardGroup>