Qwen 3.5 397B-A17B — GB200 NVL72 vs MI325X Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus MI325X (AMD CDNA 3) 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.
Near the low end of the 36–68 tok/s/user interactivity band — at 44 tok/s/user — GB200 NVL72 runs $0.04 per million tokens on Qwen 3.5 397B-A17B while MI325X runs $0.34. GB200 NVL72 is the cheaper choice by 731%.
On Qwen 3.5 397B-A17B at 52 tok/s/user, the per-million math comes out to $0.04 for GB200 NVL72 and $0.46 for MI325X; GB200 NVL72 delivers 989% more output per dollar.
At 60 tok/s/user on Qwen 3.5 397B-A17B, GB200 NVL72 costs $0.04 per million tokens; MI325X costs $0.68. GB200 NVL72 is 1437% more cost-efficient at this operating point. (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.)
Chip pricing (owning hyperscaler): GB200 NVL72 $1.86/chip/hr · MI325X $1.10/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 | GB200 NVL72:$0.041MI325X:$0.338 | GB200 NVL72:$0.042MI325X:$0.462 | GB200 NVL72:$0.044MI325X:$0.679 |
| Concurrency | GB200 NVL72:~2304MI325X:~20 | GB200 NVL72:~1876MI325X:~12 | GB200 NVL72:~1415MI325X:~7 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.