Chat Interface
Local Instance Active
Installed Models
System Resources
CPU Usage
12%
12%
GPU Memory
4.2 GB
4.2 GB
VRAM allocated to current model
RAM Usage
4.8 GB
4.8 GB
Configuration
Generation Parameters
Temperature
Controls randomness (0.0 - 2.0)
Top P
Nucleus sampling (0.0 - 1.0)
System
Active Model
The model currently loaded in memory
Context Window
Maximum tokens to remember