# Ollama benchmark

- Server: `http://192.168.0.13:11434`
- Hardware mode: CPU only (`num_gpu=0`)
- Think: forced OFF

| Model | Scenario | Runs | Prompt tok | TTFT p50 (ms) | Total p50 (ms) | tok/s p50 | Output tok (mean) |
|---|---|---|---|---|---|---|---|
| qwen3:30b-a3b | curator | 3 | 529 | 355 | 324789 | 9.8 | 3195 |
| qwen3:32b | curator | 3 | 535 | 813 | 157978 | 2.6 | 404 |
| gemma2:27b | curator | 3 | 545 | 693 | 166996 | 2.7 | 453 |
| mistral-small:22b | curator | 3 | 562 | 386 | 144660 | 3.6 | 490 |