gpu - Ollama GPU Monitoring
Monitor GPU status and performance metrics for Ollama inference
Tags
Updated: 2026-05-28Capabilities
Typical Inputs
Typical Outputs
What this skill does
- check GPU status
- monitor VRAM usage
- view loaded models
- measure inference performance
- track tokens per second
- run health check
- benchmark models
Inputs
- GPU hardware
- Ollama server API
- GPU monitoring tools
Outputs
- GPU status report
- VRAM usage data
- model list
- performance metrics
- health check results
Requirements
- Ollama server running
- GPU hardware
- nvidia-smi or rocm-smi
- Python subprocess access