Qwen 3.5 397B-A17B — GB300 NVL72 vs MI355X Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) 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 40–222 tok/s/user interactivity band — at 85 tok/s/user — GB300 NVL72 runs $0.06 per million tokens on Qwen 3.5 397B-A17B while MI355X runs $0.11. GB300 NVL72 is the cheaper choice by 84%.
On Qwen 3.5 397B-A17B at 131 tok/s/user, the per-million math comes out to $0.12 for GB300 NVL72 and $0.15 for MI355X; GB300 NVL72 delivers 23% more output per dollar.
At 177 tok/s/user on Qwen 3.5 397B-A17B, GB300 NVL72 costs $0.22 per million tokens; MI355X costs $0.25. GB300 NVL72 is 13% 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): GB300 NVL72 $2.31/chip/hr · MI355X $1.50/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:$0.058MI355X:$0.107 | GB300 NVL72:$0.125MI355X:$0.154 | GB300 NVL72:$0.222MI355X:$0.250 |
| Concurrency | GB300 NVL72:~1158MI355X:~21 | GB300 NVL72:~122MI355X:~9 | GB300 NVL72:~40MI355X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.