# Ollama benchmark

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

| Model | Scenario | Runs | Prompt tok | TTFT p50 (ms) | Total p50 (ms) | tok/s p50 | Output tok (mean) |
|---|---|---|---|---|---|---|---|
| qwen3:30b-a3b | curator | 3 | 529 | 261474 | 319287 | 9.8 | 3310 |
| qwen3:32b | curator | 3 | 529 | 127386 | 274725 | 2.5 | 756 |