# Ollama benchmark

- Server: `http://192.168.0.13:11434`
- Hardware mode: CPU only (`num_gpu=0`)
- Think: auto (chat=off, curator=on)

| Model | Scenario | Runs | Prompt tok | TTFT p50 (ms) | Total p50 (ms) | tok/s p50 | Output tok (mean) |
|---|---|---|---|---|---|---|---|
| qwen3:8b | chat | 5 | 98 | 410 | 4131 | 7.0 | 26 |
| gemma2:9b | chat | 5 | 89 | 410 | 2950 | 8.1 | 21 |
| llama3.2:3b | chat | 5 | 102 | 311 | 1627 | 21.7 | 28 |
| mistral-nemo:12b | chat | 5 | 82 | 458 | 2966 | 7.9 | 19 |