gpu - Ollama GPU Monitoring
Monitor GPU usage, VRAM, loaded models, and inference performance metrics for Ollama
Tags
Updated: 2026-05-28Capabilities
Typical Inputs
Typical Outputs
What this skill does
- check GPU status
- monitor VRAM usage
- list loaded models
- measure inference metrics
- track GPU utilization
- benchmark model performance
Inputs
- Ollama API endpoint
- nvidia-smi tool
- rocm-smi tool
Outputs
- GPU status report
- VRAM usage data
- loaded models list
- inference performance metrics
- GPU utilization readings
Requirements
- NVIDIA or AMD GPU
- Ollama server
- GPU driver installed