Qwen 3.5 397B-A17B — GB200 NVL72 vs MI300X Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus MI300X (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.
On Qwen 3.5 397B-A17B at 43 tok/s/user, the per-million math comes out to $0.12 for GB200 NVL72 and $0.89 for MI300X; GB200 NVL72 delivers 629% more output per dollar.
At 53 tok/s/user on Qwen 3.5 397B-A17B, GB200 NVL72 costs $0.32 per million tokens; MI300X costs $1.63. GB200 NVL72 is 412% more cost-efficient at this operating point.
GB200 NVL72 edges MI300X at 62 tok/s/user on Qwen 3.5 397B-A17B — $0.47 per million tokens versus $2.52, a 432% cost-per-token gap. (Numbers reflect the default 1k/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): GB200 NVL72 $2.21/GPU/hr · MI300X $1.12/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 | GB200 NVL72:$0.123MI300X:$0.893 | GB200 NVL72:$0.319MI300X:$1.633 | GB200 NVL72:$0.473MI300X:$2.517 |
| Concurrency | GB200 NVL72:~1438MI300X:~34 | GB200 NVL72:~416MI300X:~15 | GB200 NVL72:~146MI300X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.