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.
At 61 tok/s/user on Qwen 3.5 397B-A17B, GB300 NVL72 costs $0.03 per million tokens; RTX PRO 6000 costs $0.20. GB300 NVL72 is 634% more cost-efficient at this operating point.
GB300 NVL72 edges RTX PRO 6000 at 92 tok/s/user on Qwen 3.5 397B-A17B — $0.03 per million tokens versus $0.26, a 756% cost-per-token gap.
Push Qwen 3.5 397B-A17B to 123 tok/s/user and GB300 NVL72 lands at $0.03 per million tokens against RTX PRO 6000's $0.37 — GB300 NVL72 pulls ahead by 973%. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): GB300 NVL72 $2.31/chip/hr · RTX PRO 6000 $0.68/chip/hr. Source: SemiAnalysis Market July 2026 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:$0.028RTX PRO 6000:$0.203 | GB300 NVL72:$0.030RTX PRO 6000:$0.260 | GB300 NVL72:$0.035RTX PRO 6000:$0.374 |
| Concurrency | GB300 NVL72:~1536RTX PRO 6000:~8 | GB300 NVL72:~1535RTX PRO 6000:~4 | GB300 NVL72:~1068RTX PRO 6000:~2 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.