DeepSeek V4 Pro 1.6T — B200 vs MI300X
Head-to-head AI inference benchmark comparison of B200 (NVIDIA Blackwell) and MI300X (AMD CDNA 3) 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.
At 61 tok/s/user on DeepSeek V4 Pro 1.6T, B200 delivers 3770 tok/s/GPU at $0.14 per million tokens; MI300X hasn't been benchmarked at this target.
B200 hits 882 tok/s/GPU for $0.61 per million tokens at 116 tok/s/user on DeepSeek V4 Pro 1.6T. No MI300X data at this operating point.
B200: 485 tok/s/GPU, $1.14 per million tokens at 171 tok/s/user on DeepSeek V4 Pro 1.6T. MI300X is unmeasured here. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B200:3770.5MI300X:— | B200:882.2MI300X:— | B200:485.0MI300X:— |
| Cost ($/M tok) | B200:$0.144MI300X:— | B200:$0.613MI300X:— | B200:$1.144MI300X:— |
| tok/s/MW | B200:2204965MI300X:— | B200:515922MI300X:— | B200:283620MI300X:— |
| Concurrency | B200:~76MI300X:— | B200:~8MI300X:— | B200:~3MI300X:— |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.