DeepSeek V4 Pro 1.6T — GB200 NVL72 vs MI325X
Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and MI325X (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.
GB200 NVL72: 9497 tok/s/GPU, $0.06 per million tokens at 55 tok/s/user on DeepSeek V4 Pro 1.6T. MI325X is unmeasured here.
At 105 tok/s/user on DeepSeek V4 Pro 1.6T, GB200 NVL72 delivers 6644 tok/s/GPU at $0.09 per million tokens; MI325X hasn't been benchmarked at this target.
GB200 NVL72 hits 526 tok/s/GPU for $1.17 per million tokens at 154 tok/s/user on DeepSeek V4 Pro 1.6T. No MI325X data at this operating point. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | GB200 NVL72:9497.1MI325X:— | GB200 NVL72:6644.2MI325X:— | GB200 NVL72:525.8MI325X:— |
| Cost ($/M tok) | GB200 NVL72:$0.065MI325X:— | GB200 NVL72:$0.093MI325X:— | GB200 NVL72:$1.169MI325X:— |
| tok/s/MW | GB200 NVL72:5078682MI325X:— | GB200 NVL72:3553038MI325X:— | GB200 NVL72:281160MI325X:— |
| Concurrency | GB200 NVL72:~16349MI325X:— | GB200 NVL72:~2152MI325X:— | GB200 NVL72:~45MI325X:— |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.