4090D
2 records across 1 models (quants: FP8, W4A16).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 4090D | Qwen2.5-14B 14B dense | FP8 | vLLM | 1131.19 | – | – | – | – | 2026-03 | community | – | source |
| 4090D | Qwen2.5-14B 14B dense | W4A16 | vLLM | 1079.15 | – | – | – | – | 2026-03 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085