DeepSeek R1 — GB300 NVL72 vs MI355X
Head-to-head AI inference benchmark comparison of GB300 NVL72 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) 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.
Throughput at 95 tok/s/user on DeepSeek R1: GB300 NVL72 hits 12350 tok/s/GPU, MI355X hits 7592. Per-million costs land at $0.06 and $0.05 respectively. MI355X is 11% cheaper per token; GB300 NVL72 delivers 63% more tok/s/GPU.
GB300 NVL72 / MI355X on DeepSeek R1 at 167 tok/s/user: 4744 / 1909 tok/s/GPU, $0.16 / $0.22 per million tokens. GB300 NVL72 is 41% cheaper per token; GB300 NVL72 delivers 148% more tok/s/GPU.
Toward the upper edge of the 23–312 tok/s/user interactivity band, at 240 tok/s/user on DeepSeek R1: GB300 NVL72 runs 961 tok/s/GPU at $0.77/M tokens, MI355X runs 538 at $0.76/M. Cost per token is essentially tied; GB300 NVL72 delivers 79% more tok/s/GPU. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | GB300 NVL72:12350.5MI355X:7592.3 | GB300 NVL72:4743.7MI355X:1909.0 | GB300 NVL72:961.3MI355X:538.1 |
| Cost ($/M tok) | GB300 NVL72:$0.060MI355X:$0.054 | GB300 NVL72:$0.155MI355X:$0.218 | GB300 NVL72:$0.765MI355X:$0.764 |
| tok/s/MW | GB300 NVL72:5881190MI355X:2865006 | GB300 NVL72:2258892MI355X:720368 | GB300 NVL72:457768MI355X:203070 |
| Concurrency | GB300 NVL72:~690MI355X:~204 | GB300 NVL72:~181MI355X:~55 | GB300 NVL72:~23MI355X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.