RTX 6000 Pro (96GB)
1 records across 1 models (quants: Q2).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX 6000 Pro (96GB) | DeepSeek-V4-Flash | Q2 | llama.cpp (CUDA) | 35 | – | – | – | – | 2026-05-26 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085