# Ollama benchmark

- Server: `http://192.168.0.9:11434`
- 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 | 183 | 164198 | 17.4 | 2732 |
| qwen3:32b | curator | 3 | 535 | 677 | 136519 | 3.0 | 406 |
| gemma2:27b | curator | 3 | 545 | 392 | 132739 | 3.7 | 451 |
| mistral-small:22b | curator | 3 | 562 | 293 | 105971 | 4.7 | 485 |