MLX-GUI Admin

Version {{ version }}

System Online

0GB / 0GB

System Status: Healthy

Loaded Models: 0

Memory Usage: 0%

Queue Size: 0

Installed Models

Discover MLX Models

System Information

Model Statistics

API Test Console

Test Configuration

Select Model

Message

Max Tokens

Temperature

System Message (optional)

Response

Response will appear here

Response Time: -ms

Tokens Generated: -

Model: -

Request History

No tests run yet

Settings

Model Management

Auto-unload Inactive Models

Inactivity Timeout (minutes)

System Settings

Max Concurrent Models

Log Level

Network Settings

Server Port

Port number for the server (1-65535). Default is 8000.

Bind to All Interfaces

Allow access from other devices on your network (0.0.0.0). ⚠️ Security Risk: Only enable on trusted networks.

MLX-GUI - Apple Silicon AI Model Server v{{ version }}

By Matthew Rogers (@RamboRogers)

View on GitHub | GPL v3 License

Loading...

Initializing... 0s

Server Restart Required

Network settings have changed (port or bind settings). The server needs to restart for changes to take effect.