DeepSeek R1 — GB300 NVL72 vs Vera Rubin NVL72
Head-to-head AI inference benchmark comparison of GB300 NVL72 (NVIDIA Blackwell) and Vera Rubin NVL72 (NVIDIA Vera Rubin) 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 117 tok/s/user interactivity on DeepSeek R1, GB300 NVL72 delivers 10415 tok/s/chip at $0.06 per million tokens; Vera Rubin NVL72 delivers 0 tok/s/chip at $0.00. Comparable data is unavailable at this point.
GB300 NVL72 posts 2834 tok/s/chip for $0.23 per million tokens at 182 tok/s/user on DeepSeek R1; Vera Rubin NVL72 posts 0 tok/s/chip for $0.00. Comparable data is unavailable.
Throughput at 247 tok/s/user on DeepSeek R1: GB300 NVL72 hits 884 tok/s/chip, Vera Rubin NVL72 hits 0. Per-million costs land at $0.73 and $0.00 respectively. Comparable data is unavailable. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB300 NVL72:10415.4Vera Rubin NVL72:0.0 | GB300 NVL72:2834.2Vera Rubin NVL72:0.0 | GB300 NVL72:883.9Vera Rubin NVL72:0.0 |
| Cost ($/M tok) | GB300 NVL72:$0.062Vera Rubin NVL72:$0.000 | GB300 NVL72:$0.226Vera Rubin NVL72:$0.000 | GB300 NVL72:$0.726Vera Rubin NVL72:$0.000 |
| tok/s/MW | GB300 NVL72:4912948Vera Rubin NVL72:0 | GB300 NVL72:1336868Vera Rubin NVL72:0 | GB300 NVL72:416931Vera Rubin NVL72:0 |
| Concurrency | GB300 NVL72:~485Vera Rubin NVL72:~400 | GB300 NVL72:~84Vera Rubin NVL72:~400 | GB300 NVL72:~19Vera Rubin NVL72:~400 |