Qwen 3.5 397B-A17B — GB300 NVL72 vs RTX PRO 6000
Head-to-head AI inference benchmark comparison of GB300 NVL72 (NVIDIA Blackwell) and RTX PRO 6000 (NVIDIA Blackwell) on Qwen 3.5 397B-A17B. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
At 123 tok/s/user on Qwen 3.5 397B-A17B, GB300 NVL72 delivers 6206 tok/s/GPU at $0.12 per million tokens; RTX PRO 6000 hasn't been benchmarked at this target.
GB300 NVL72 hits 1960 tok/s/GPU for $0.38 per million tokens at 207 tok/s/user on Qwen 3.5 397B-A17B. No RTX PRO 6000 data at this operating point.
GB300 NVL72: 772 tok/s/GPU, $0.92 per million tokens at 291 tok/s/user on Qwen 3.5 397B-A17B. RTX PRO 6000 is unmeasured here. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | GB300 NVL72:6206.5RTX PRO 6000:— | GB300 NVL72:1960.3RTX PRO 6000:— | GB300 NVL72:771.8RTX PRO 6000:— |
| Cost ($/M tok) | GB300 NVL72:$0.122RTX PRO 6000:— | GB300 NVL72:$0.379RTX PRO 6000:— | GB300 NVL72:$0.916RTX PRO 6000:— |
| tok/s/MW | GB300 NVL72:2927579RTX PRO 6000:— | GB300 NVL72:924687RTX PRO 6000:— | GB300 NVL72:364073RTX PRO 6000:— |
| Concurrency | GB300 NVL72:~212RTX PRO 6000:— | GB300 NVL72:~20RTX PRO 6000:— | GB300 NVL72:~3RTX PRO 6000:— |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.