4x RTX A6000
2 records across 1 models (quants: Q8_K_XL).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 4x RTX A6000 | DeepSeek-V4-Flash | Q8_K_XL | llama.cpp | 33 | – | – | – | 1048576 | 2026-09 | community | – | source |
| 4x RTX A6000 | DeepSeek-V4-Flash | Q8_K_XL | llama.cpp | 11.7 | – | – | – | 1048576 | 2026-09 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085