Qwen 3.5 397B-A17B — GB300 NVL72 vs RTX PRO 6000 Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus RTX PRO 6000 (NVIDIA Blackwell) on Qwen 3.5 397B-A17B. Owning-hyperscaler TCO normalized by output tokens — performance per dollar across LLM workloads. Pick the more cost-efficient SKU at every target interactivity level. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
GB300 NVL72 costs $0.12 per million tokens at 123 tok/s/user on Qwen 3.5 397B-A17B; we have no RTX PRO 6000 benchmark data at this exact target.
At 207 tok/s/user on Qwen 3.5 397B-A17B, GB300 NVL72 comes in at $0.38 per million tokens. RTX PRO 6000 hasn't been benchmarked at this operating point.
Only GB300 NVL72 has cost data at 291 tok/s/user on Qwen 3.5 397B-A17B — $0.92 per million tokens. RTX PRO 6000 is unmeasured at this target. (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.)
GPU pricing (owning hyperscaler): GB300 NVL72 $2.65/GPU/hr · RTX PRO 6000 $0.43/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | GB300 NVL72:$0.122RTX PRO 6000:— | GB300 NVL72:$0.379RTX PRO 6000:— | GB300 NVL72:$0.916RTX 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.