A100 PCIe
2 records across 1 models (quants: FP8).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| A100 PCIe | Qwen3-VL-30B-A3B-Instruct-FP8 30B MoE A3B VLM | FP8 | vLLM | 689.02 | – | – | – | – | 2025-10 | community | – | source |
| A100 PCIe | Qwen3-VL-30B-A3B-Instruct-FP8 30B MoE A3B VLM | FP8 | vLLM | 681.42 | – | – | – | – | 2025-10 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085