LLM Models

Running models: 0 / 2

GPU utilization reserved: 0.00 / 0.98

Limits: max 2 running models and combined configured GPU utilization must be less than 0.98.

Create LLM Model

ID	Name	Served	Backend	Host	Port	GPU Util	Status	Actions
2	laguna-xs Laguna XS	laguna-xs	vllm	127.0.0.1	11434	0.95	stopped not running	Edit Arguments
1	North Code North	north-code	vllm	127.0.0.1	11434	0.95	stopped not running	Edit Arguments