Qwen4-exp
2 records across 1 hardware.
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX PRO 6000 | Qwen4-exp | unspecified | llama.cpp (CUDA) | – | 3867 | – | – | 131072 | 2026-10-03 | community | – | source |
| RTX PRO 6000 | Qwen4-exp | unspecified | llama.cpp (CUDA) | – | 4038 | – | – | 131072 | 2026-10-03 | community | – | source |