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. Large-hyperscaler-volume ownership TCO normalized by total 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 $0.05 per million tokens on Qwen 3.5 397B-A17B while RTX PRO 6000 runs $0.18. MI355X is the cheaper choice by 224%.
On Qwen 3.5 397B-A17B at 82 tok/s/user, the per-million math comes out to $0.07 for MI355X and $0.24 for RTX PRO 6000; MI355X delivers 236% more total tokens per dollar.
At 118 tok/s/user on Qwen 3.5 397B-A17B, MI355X costs $0.09 per million tokens; RTX PRO 6000 costs $0.35. MI355X is 296% 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:$0.055RTX PRO 6000:$0.177 | MI355X:$0.071RTX PRO 6000:$0.237 | MI355X:$0.089RTX PRO 6000:$0.351 |
| Concurrency | MI355X:~37RTX PRO 6000:~12 | MI355X:~17RTX PRO 6000:~5 | MI355X:~9RTX PRO 6000:~2 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
Qwen3.5 397B 8K / 1K Cost per Million Total Tokens vs. Interactivity
Qwen3.5 397B 8K / 1K Cost per Million Total Tokens vs. Interactivity- Cost Tier:
- Source:
- SemiAnalysis InferenceX™
TCO $/chip/hr:
Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate cost per million tokens per decode chip or per prefill chip, rather than per total chip count. This makes direct token cost comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate input throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct input throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate output throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct output throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate power per decode chip or per prefill chip, rather than per total chip count. This makes direct power comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate Joules per decode chip or per prefill chip, rather than per total chip count. This makes direct Joules per token comparison with aggregated configs not an apples-to-apples comparison.
No data available
Matching measurements exist, but their chip series are hidden.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip
1 The ATOM engine is promising, however it has yet to serve production tokens. It is still in its infant stage.