| **P2P_TOKEN** | Token to use for the federation or for starting workers. See [distributed inferencing documentation]({{%relref "features/distributed_inferencing" %}}) |
| **WORKER** | Set to `"true"` to make the instance a worker (p2p token is required) |
| **FEDERATED** | Set to `"true"` to share the instance with the federation (p2p token is required) |
| **FEDERATED_SERVER** | Set to `"true"` to run the instance as a federation server which forwards requests to the federation (p2p token is required) |
#### Image Selection
The installer will automatically detect your GPU and select the appropriate image. By default, it uses the standard images without extra Python dependencies. You can customize the image selection:
-`USE_AIO=true`: Use all-in-one images that include all dependencies
-`USE_VULKAN=true`: Use Vulkan GPU support instead of vendor-specific GPU support
#### Uninstallation
To uninstall LocalAI installed via the script:
```bash
curl https://localai.io/install.sh | sh -s -- --uninstall
```
## Manual Installation
### Download Binary
You can manually download the appropriate binary for your system from the [releases page](https://github.com/mudler/LocalAI/releases):
1. Go to [GitHub Releases](https://github.com/mudler/LocalAI/releases)
2. Download the binary for your architecture (amd64, arm64, etc.)
3. Make it executable:
```bash
chmod +x local-ai-*
```
4. Run LocalAI:
```bash
./local-ai-*
```
### System Requirements
Hardware requirements vary based on:
- Model size
- Quantization method
- Backend used
For performance benchmarks with different backends like `llama.cpp`, visit [this link](https://github.com/ggerganov/llama.cpp#memorydisk-requirements).
## Configuration
After installation, you can:
- Access the WebUI at `http://localhost:8080`
- Configure models in the models directory
- Customize settings via environment variables or config files
