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 72 tok/s/user on DeepSeek R1: GB300 NVL72 hits 11871 tok/s/GPU, MI355X hits 1787. Per-million costs land at $0.06 and $0.23 respectively. GB300 NVL72 is 272% cheaper per token; GB300 NVL72 delivers 564% more tok/s/GPU.
GB300 NVL72 / MI355X on DeepSeek R1 at 130 tok/s/user: 4591 / 420 tok/s/GPU, $0.16 / $0.99 per million tokens. GB300 NVL72 is 517% cheaper per token; GB300 NVL72 delivers 993% more tok/s/GPU.
Toward the upper edge of the 15–244 tok/s/user interactivity band, at 187 tok/s/user on DeepSeek R1: GB300 NVL72 runs 865 tok/s/GPU at $0.90/M tokens, MI355X runs 184 at $2.23/M. GB300 NVL72 is 148% cheaper per token; GB300 NVL72 delivers 369% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | GB300 NVL72:11871.2MI355X:1787.3 | GB300 NVL72:4590.9MI355X:420.2 | GB300 NVL72:864.6MI355X:184.3 |
| Cost ($/M tok) | GB300 NVL72:$0.062MI355X:$0.231 | GB300 NVL72:$0.161MI355X:$0.991 | GB300 NVL72:$0.899MI355X:$2.231 |
| tok/s/MW | GB300 NVL72:5652964MI355X:674464 | GB300 NVL72:2186163MI355X:158555 | GB300 NVL72:411710MI355X:69552 |
| Concurrency | GB300 NVL72:~2185MI355X:~251 | GB300 NVL72:~906MI355X:~21 | GB300 NVL72:~123MI355X:~4 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.