Qwen2.5 Coder 3B same-model 3-up
Combined system throughput 12.407 tok/s, primary system throughput 6.839 tok/s, wall time 293.458s.
- Parallel speedup: 2.634
- Wall savings: 62.0%
- Usable primary/follow-up: 20/20
This run selected the historically fastest local-Mac question types, repeated them into one focused packet, and then swept concurrency upward until throughput clearly stopped improving.
Peak combined system throughput: 16.057 tok/s at 4-up. Practical plateau start: 4-up.
| Question | Category | Avg primary TPS | Avg follow-up TPS | Avg combined TPS |
|---|---|---|---|---|
| py_csv_parse | parsing | 31.89 | 26.99 | 58.88 |
| py_cli_args | cli | 25.82 | 26.65 | 52.47 |
| py_pydantic_model | validation | 25.78 | 25.85 | 51.62 |
| py_typing_dataclass | typing | 26.29 | 23.55 | 49.84 |
| py_file_scan | file_io | 23.82 | 25.67 | 49.49 |
| Concurrency | Combined system TPS | Primary system TPS | Parallel speedup | Total wall seconds |
|---|---|---|---|---|
| 3 | 12.407 | 6.839 | 2.634 | 293.458 |
| 4 | 16.057 | 8.173 | 2.516 | 225.253 |
| 5 | 13.862 | 7.646 | 4.585 | 248.877 |
| 6 | 15.712 | 8.425 | 3.369 | 226.832 |
| 7 | 13.488 | 7.557 | 5.996 | 270.096 |
Combined system throughput 12.407 tok/s, primary system throughput 6.839 tok/s, wall time 293.458s.
Combined system throughput 16.057 tok/s, primary system throughput 8.173 tok/s, wall time 225.253s.
Combined system throughput 13.862 tok/s, primary system throughput 7.646 tok/s, wall time 248.877s.
Combined system throughput 15.712 tok/s, primary system throughput 8.425 tok/s, wall time 226.832s.
Combined system throughput 13.488 tok/s, primary system throughput 7.557 tok/s, wall time 270.096s.