Qwen 3.5 397B-A17B — GB300 NVL72 vs MI325X Performance per Dollar
Cost per million tokens of GB300 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.
At 55 tok/s/user on Qwen 3.5 397B-A17B, MI325X comes in at $0.89 per million tokens. GB300 NVL72 hasn't been benchmarked at this operating point.
Only MI325X has cost data at 70 tok/s/user on Qwen 3.5 397B-A17B — $1.30 per million tokens. GB300 NVL72 is unmeasured at this target.
MI325X costs $2.09 per million tokens at 84 tok/s/user on Qwen 3.5 397B-A17B; we have no GB300 NVL72 benchmark data at this exact target. (Numbers reflect the default 1k/1k · bf16 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 · MI325X $1.28/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:—MI325X:$0.891 | GB300 NVL72:—MI325X:$1.298 | GB300 NVL72:—MI325X:$2.090 |
| Concurrency | GB300 NVL72:—MI325X:~32 | GB300 NVL72:—MI325X:~16 | GB300 NVL72:—MI325X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.