target http://localhost:11434, model qwen3:4b, generated 2026-09-30 08:12 UTC
Request Idle Score at concurrency 1. This is the percentage of the test window where the server had zero requests in flight (or, with a hardware sampler, where the GPU itself was not active). A high number here at concurrency 1 reflects one user's think-time between messages, not a broken server. See idle percent drop as concurrency rises below.
sampler: ollama-timing (no passwordless sudo for powermetrics, falling back to request-timing inference (run `sudo visudo` to add a NOPASSWD rule for powermetrics if you want hardware samples instead))
| concurrency | idle % | busy % | tok/s | p50 latency s | p95 latency s | ok | failed |
|---|---|---|---|---|---|---|---|
| 1 | 38.5 | 61.5 | 25.6 | 3.097 | 3.262 | 12 | 0 |
| 16 | 0.0 | 100.0 | 38.8 | 47.632 | 53.38 | 34 | 0 |