Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.
Install
npx skills add NVIDIA/skills --skill jetson-llm-benchmarknpx skills add NVIDIA/skills --skill jetson-llm-benchmark -a claude-code -gnpx skills add NVIDIA/skills --skill jetson-llm-benchmark -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/jetson-llm-benchmarkgh skill install NVIDIA/skills jetson-llm-benchmarkgit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/jetson-llm-benchmark ~/.claude/skills/jetson-llm-benchmark # Claude Code
cp -R /tmp/NVIDIA__skills/skills/jetson-llm-benchmark ~/.agents/skills/jetson-llm-benchmark # Codex, Cursor, Gemini CLI, Copilot, OpenCode