Qwen 3.5 397B-A17B — B200 vs MI355X
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) on Qwen 3.5 397B-A17B. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
At 82 tok/s/user interactivity on Qwen 3.5 397B-A17B, B200 delivers 2481 tok/s/GPU at $0.22 per million tokens; MI355X delivers 1598 tok/s/GPU at $0.26. B200 is 19% cheaper per token; B200 delivers 55% more tok/s/GPU at this point.
B200 posts 1115 tok/s/GPU for $0.48 per million tokens at 134 tok/s/user on Qwen 3.5 397B-A17B; MI355X posts 903 tok/s/GPU for $0.46. MI355X is 6% cheaper per token; B200 delivers 24% more tok/s/GPU.
Throughput at 185 tok/s/user on Qwen 3.5 397B-A17B: B200 hits 720 tok/s/GPU, MI355X hits 510. Per-million costs land at $0.75 and $0.78 respectively. B200 is 4% cheaper per token; B200 delivers 41% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B200:2480.6MI355X:1597.6 | B200:1115.3MI355X:902.8 | B200:719.6MI355X:510.4 |
| Cost ($/M tok) | B200:$0.219MI355X:$0.261 | B200:$0.484MI355X:$0.458 | B200:$0.751MI355X:$0.781 |
| tok/s/MW | B200:1143133MI355X:602871 | B200:513974MI355X:340690 | B200:331610MI355X:192596 |
| Concurrency | B200:~68MI355X:~40 | B200:~19MI355X:~13 | B200:~9MI355X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.