Qwen3.8
8 records across 2 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M4 Max | Qwen3.8 | oQ4e | oMLX | 47.9 | 255.4 | – | – | 4096 | 2026-10-09 | community | – | source |
| 3x RTX PRO 4000 Blackwell | Qwen3.8 | unspecified | CUDA | 41.6 | 1756 | – | – | 262144 | 2026-10 | community | – | source |
| 3x RTX PRO 4000 Blackwell | Qwen3.8 | unspecified | CUDA | 40.8 | 952 | – | – | 262144 | 2026-10 | community | – | source |
| M4 Max | Qwen3.8 | oQ4e | oMLX | 34.6 | 230.0 | – | – | 32768 | 2026-10-09 | community | – | source |
| 3x RTX PRO 4000 Blackwell | Qwen3.8 | unspecified | CUDA | – | 1254 | – | – | – | 2026-10 | community | – | source |
| 3x RTX PRO 4000 Blackwell | Qwen3.8 | unspecified | CUDA | – | 1496 | – | – | – | 2026-10 | community | – | source |
| 3x RTX PRO 4000 Blackwell | Qwen3.8 | unspecified | CUDA | – | 1685 | – | – | – | 2026-10 | community | – | source |
| 3x RTX PRO 4000 Blackwell | Qwen3.8 | unspecified | CUDA | – | 1314 | – | – | – | 2026-10 | community | – | source |