DeepSeek R1 — GB200 NVL72 vs MI300X
Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and MI300X (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.
At 85 tok/s/user on DeepSeek R1, GB200 NVL72 delivers 7753 tok/s/GPU at $0.08 per million tokens; MI300X hasn't been benchmarked at this target.
GB200 NVL72 hits 1361 tok/s/GPU for $0.45 per million tokens at 152 tok/s/user on DeepSeek R1. No MI300X data at this operating point.
GB200 NVL72: 291 tok/s/GPU, $2.11 per million tokens at 219 tok/s/user on DeepSeek R1. MI300X is unmeasured here. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | GB200 NVL72:7753.2MI300X:— | GB200 NVL72:1360.9MI300X:— | GB200 NVL72:290.7MI300X:— |
| Cost ($/M tok) | GB200 NVL72:$0.079MI300X:— | GB200 NVL72:$0.447MI300X:— | GB200 NVL72:$2.110MI300X:— |
| tok/s/MW | GB200 NVL72:3691993MI300X:— | GB200 NVL72:648067MI300X:— | GB200 NVL72:138416MI300X:— |
| Concurrency | GB200 NVL72:~2246MI300X:— | GB200 NVL72:~226MI300X:— | GB200 NVL72:~27MI300X:— |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.