DeepSeek V4 Pro 1.6T — B200 vs MI355X
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) on DeepSeek V4 Pro 1.6T. 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.
Throughput at 34 tok/s/user on DeepSeek V4 Pro 1.6T: B200 hits 1411 tok/s/GPU, MI355X hits 912. Per-million costs land at $0.39 and $0.45 respectively. B200 is 17% cheaper per token; B200 delivers 55% more tok/s/GPU.
B200 / MI355X on DeepSeek V4 Pro 1.6T at 65 tok/s/user: 364 / 340 tok/s/GPU, $1.45 / $1.22 per million tokens. MI355X is 19% cheaper per token; B200 delivers 7% more tok/s/GPU.
Toward the upper edge of the 4–127 tok/s/user interactivity band, at 97 tok/s/user on DeepSeek V4 Pro 1.6T: B200 runs 188 tok/s/GPU at $2.90/M tokens, MI355X runs 201 at $2.03/M. MI355X is 43% cheaper per token; MI355X delivers 7% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B200:1411.1MI355X:912.3 | B200:363.8MI355X:339.9 | B200:188.2MI355X:200.5 |
| Cost ($/M tok) | B200:$0.387MI355X:$0.451 | B200:$1.454MI355X:$1.224 | B200:$2.895MI355X:$2.032 |
| tok/s/MW | B200:650267MI355X:344257 | B200:167628MI355X:128274 | B200:86732MI355X:75667 |
| Concurrency | B200:~184MI355X:~126 | B200:~24MI355X:~23 | B200:~9MI355X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.