Qwen 3.5 397B-A17B — MI355X vs RTX PRO 6000 Performance per Dollar
Cost per million tokens of MI355X (AMD CDNA 4) 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.
Near the low end of the 11–153 tok/s/user interactivity band — at 47 tok/s/user — MI355X runs $0.07 per million tokens on Qwen 3.5 397B-A17B while RTX PRO 6000 runs $0.18. MI355X is the cheaper choice by 170%.
On Qwen 3.5 397B-A17B at 82 tok/s/user, the per-million math comes out to $0.09 for MI355X and $0.24 for RTX PRO 6000; MI355X delivers 174% more output per dollar.
At 118 tok/s/user on Qwen 3.5 397B-A17B, MI355X costs $0.11 per million tokens; RTX PRO 6000 costs $0.35. MI355X is 209% more cost-efficient at this operating point. (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): MI355X $1.50/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 | MI355X:$0.065RTX PRO 6000:$0.177 | MI355X:$0.087RTX PRO 6000:$0.237 | MI355X:$0.114RTX PRO 6000:$0.351 |
| Concurrency | MI355X:~31RTX PRO 6000:~12 | MI355X:~13RTX PRO 6000:~5 | MI355X:~7RTX PRO 6000:~2 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.