Lightweight shell script to benchmark token generation speed (tok/s) across Ollama models running in Docker. Auto-discovers all installed models or accepts a custom list via CLI. Uses Ollama's internal eval_duration timing for accurate results — no dependencies beyond curl and awk.
shell docker benchmarking benchmark gpu inference unraid compare token tokenization llm ollama llm-benchmark tokens-per-second ollama-benchmark
-
Updated
Apr 18, 2026 - Shell