8x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition (96 GB each)
2 records across 2 models (quants: FP8).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 8x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition (96 GB each) | DeepSeek-V4.1-Flash | FP8 | vLLM | 4.0 | – | – | – | – | 2026-09-27 | community | – | source |
| 8x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition (96 GB each) | DS-V4-Flash | FP8 | vLLM | 2452 | – | – | – | – | 2026-09-27 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085