Qwen3-30B-A3B-Instruct-2507-FP8
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 5000 72GB | Qwen3-30B-A3B-Instruct-2507-FP8 | FP8 | vLLM | 19806 | – | – | – | 4096 | 2026-09-28 | community | – | source |
| RTX PRO 5000 72GB | Qwen3-30B-A3B-Instruct-2507-FP8 | FP8 | vLLM | 19778 | – | – | – | 4096 | 2026-09-28 | community | – | source |