M

ModelOps Gateway

System Ready
Uptime: 142h 12m

Active Models

12 / 16

GPU Compute

42.8%

Storage Used

1.2 TB

Network Latency

4ms

Model Catalog

Model Name Type Format Status Action
Llama-3-70B-Instruct-v1 LLM / NLP GGUF ● Loaded
Stable-Diffusion-XL-Base Image Gen Safetensors ● Idle
Mistral-7B-v0.3-MoE LLM PyTorch ● Loaded