> ## Documentation Index
> Fetch the complete documentation index at: https://forge-64364c0e.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Installation

> System requirements and how to install ForgeAI

## System Requirements

<CardGroup cols={2}>
  <Card title="Minimum" icon="hard-drive">
    * **OS**: Linux, macOS, or Windows
    * **RAM**: 8 GB
    * **Disk**: 2 GB + space for your models
    * **CPU**: x86\_64 or ARM64
  </Card>

  <Card title="Recommended" icon="rocket">
    * **RAM**: 16 GB+
    * **GPU**: NVIDIA (CUDA), AMD (Vulkan), or Apple Silicon (Metal)
    * **Disk**: SSD with 50 GB+ free
    * **Python 3.10+** for Training & Convert
  </Card>
</CardGroup>

## Install from Release

<Steps>
  <Step title="Download the release">
    Download the latest release for your platform from the [releases page](https://github.com/siddhesh2377/ForgeAi/releases).

    | Platform | File                                     |
    | -------- | ---------------------------------------- |
    | Linux    | `forgeai_x.x.x_amd64.AppImage` or `.deb` |
    | macOS    | `ForgeAI_x.x.x.dmg`                      |
    | Windows  | `ForgeAI_x.x.x_x64-setup.exe`            |
  </Step>

  <Step title="Run the installer">
    * **Linux**: Make the AppImage executable (`chmod +x`) and run, or install the `.deb`
    * **macOS**: Open the `.dmg` and drag ForgeAI to Applications
    * **Windows**: Run the setup executable
  </Step>

  <Step title="First launch">
    Open ForgeAI. You'll land on the Dashboard (module 00).
  </Step>
</Steps>

## Build from Source

<Steps>
  <Step title="Install prerequisites">
    * [Rust](https://rustup.rs/) (latest stable)
    * [Node.js](https://nodejs.org/) (v20+)
    * [Tauri v2 prerequisites](https://v2.tauri.app/start/prerequisites/) for your OS
  </Step>

  <Step title="Clone and install">
    ```bash theme={null}
    git clone https://github.com/siddhesh2377/ForgeAi.git
    cd ForgeAi
    npm install
    ```
  </Step>

  <Step title="Run in development mode">
    ```bash theme={null}
    npm run tauri dev
    ```
  </Step>

  <Step title="Build for production">
    ```bash theme={null}
    npm run tauri build
    ```

    The compiled binary will be in `src-tauri/target/release/`.
  </Step>
</Steps>

## Optional: GPU Setup

For accelerated inference and training:

<Tabs>
  <Tab title="NVIDIA (CUDA)">
    1. Install NVIDIA drivers (515+ recommended)
    2. CUDA toolkit is bundled with llama.cpp — no separate install needed
    3. In ForgeAI Settings, install llama.cpp with the **CUDA** variant
    4. For training, CUDA 11.8+ is required (PyTorch auto-detects during setup)
  </Tab>

  <Tab title="AMD / Intel (Vulkan)">
    1. Install Vulkan drivers for your GPU
    2. In ForgeAI Settings, install llama.cpp with the **Vulkan** variant
    3. Training is CPU-only on AMD/Intel (PyTorch CUDA not available)
  </Tab>

  <Tab title="Apple Silicon (Metal)">
    1. Metal is built into macOS — no extra drivers needed
    2. In ForgeAI Settings, install llama.cpp with the default variant
    3. Training uses MPS (Metal Performance Shaders) automatically
  </Tab>

  <Tab title="CPU Only">
    No extra setup needed. In ForgeAI Settings, install llama.cpp with the **CPU** variant.
  </Tab>
</Tabs>

## Optional: Python (for Training & Convert)

Both the **Training** module and **Convert** module require Python 3.10+. Each uses its own isolated virtual environment.

<Steps>
  <Step title="Verify Python">
    ```bash theme={null}
    python3 --version
    ```

    If not installed, get it from [python.org](https://python.org) or your package manager.
  </Step>

  <Step title="Auto-setup in ForgeAI">
    Navigate to the Training or Convert module. ForgeAI will detect Python and prompt you to install dependencies. Each environment is a one-time setup:

    | Environment | Size     | Packages                                        |
    | ----------- | -------- | ----------------------------------------------- |
    | Training    | \~2 GB   | PyTorch, Transformers, PEFT, TRL, BitsAndBytes  |
    | Convert     | \~500 MB | Transformers, Torch, SafeTensors, SentencePiece |

    You can also manage both environments from **Settings** (07).
  </Step>
</Steps>