DeepSeek R1 — GB200 NVL72 vs MI325X
Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and MI325X (AMD CDNA 3) on DeepSeek R1. 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: 7753 tok/s/GPU, $0.08 per million tokens at 85 tok/s/user on DeepSeek R1. MI325X is unmeasured here.
At 152 tok/s/user on DeepSeek R1, GB200 NVL72 delivers 1361 tok/s/GPU at $0.45 per million tokens; MI325X hasn't been benchmarked at this target.
GB200 NVL72 hits 291 tok/s/GPU for $2.11 per million tokens at 219 tok/s/user on DeepSeek R1. No MI325X data at this operating point. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | GB200 NVL72:7753.2MI325X:— | GB200 NVL72:1360.9MI325X:— | GB200 NVL72:290.7MI325X:— |
| Cost ($/M tok) | GB200 NVL72:$0.079MI325X:— | GB200 NVL72:$0.447MI325X:— | GB200 NVL72:$2.110MI325X:— |
| tok/s/MW | GB200 NVL72:3691993MI325X:— | GB200 NVL72:648067MI325X:— | GB200 NVL72:138416MI325X:— |
| Concurrency | GB200 NVL72:~2246MI325X:— | GB200 NVL72:~226MI325X:— | GB200 NVL72:~27MI325X:— |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.