deepseek-r1 · Server
deepseek-r1 / Server / Tokens/s
v6.0|closed|deepseek-r1|Server|Tokens/s|official-system
Metric: Performance_Result (Tokens/s) · winning: higher · 18 ranking-eligible rows · vendors 1 · families 2 · never mixed with other slices
All systems (official)
| Rank | Performance | Unit | System | Submitter | Accelerator | Source |
|---|---|---|---|---|---|---|
| 1 | 1,555,110.0000 | Tokens/s | NVIDIA GB300 NVL72 (72x GB300-288GB_aarch64, TensorRT) | NVIDIA | NVIDIA GB300 | source |
| 2 | 575,580.0000 | Tokens/s | Nebius GB300 NVL72 (72x GB300-288GB_aarch64, TensorRT) | Nebius | NVIDIA GB300 | source |
| 3 | 400,437.0000 | Tokens/s | NVIDIA GB300 NVL72 (72x GB300-288GB_aarch64, TensorRT) | NVIDIA | NVIDIA GB300 | source |
| 4 | 336,106.0000 | Tokens/s | NVIDIA GB200 NVL72 (72x GB200-186GB_aarch64, TensorRT) | NVIDIA | NVIDIA GB200 | source |
| 5 | 311,531.0000 | Tokens/s | CoreWeave GB200 NVL72 (64x GB200-186GB_aarch64, TensorRT) | CoreWeave | NVIDIA GB200 | source |
| 6 | 156,781.0000 | Tokens/s | NVIDIA GB200 NVL72 (72x GB200-186GB_aarch64, TensorRT) | NVIDIA GB200 | source | |
| 7 | 64,510.0000 | Tokens/s | Nebius GB300 NVL72 (4x GB300-288GB_aarch64, TensorRT) | Nebius | NVIDIA GB300 | source |
| 8 | 60,413.4000 | Tokens/s | Nebius B300 n1 (8x B300-SXM-270GB, TensorRT) | Nebius | NVIDIA B300-SXM-270GB | source |
| 9 | 58,553.3000 | Tokens/s | Cisco UCS C880A M8 (8x NVIDIA B300-SXM-270GB, TensorRT) | Cisco | NVIDIA B300-SXM-270GB | source |
| 10 | 51,692.9000 | Tokens/s | Nebius B200 n1 (8x B200-SXM-180GB, TensorRT) | Nebius | NVIDIA B200-SXM-180GB | source |
| 11 | 46,513.1000 | Tokens/s | PowerEdge XE9780 (8x B300-SXM-270GB, TensorRT) | Dell | NVIDIA B300-SXM-270GB | source |
| 12 | 46,510.6000 | Tokens/s | PowerEdge XE9780L (8x B300-SXM-270GB, TensorRT) | Dell | NVIDIA B300-SXM-270GB | source |
| 13 | 44,589.7000 | Tokens/s | CoreWeave GB300 NVL72 (8x GB300-288GB_aarch64, TensorRT) | CoreWeave | NVIDIA GB300 | source |
| 14 | 42,721.4000 | Tokens/s | NVIDIA DGX B300 (8x B300-SXM-270GB, TensorRT) | NVIDIA | NVIDIA B300-SXM-270GB | source |
| 15 | 41,027.9000 | Tokens/s | NVIDIA DGX B200 (8x B200-SXM-180GB, TensorRT) | NVIDIA B200-SXM-180GB | source | |
| 16 | 40,949.5000 | Tokens/s | PowerEdge XE9780 (8x B200-SXM-180GB, TensorRT) | Dell | NVIDIA B200-SXM-180GB | source |
| 17 | 35,552.6000 | Tokens/s | G894-SD3-AAX7 | GigaComputing | NVIDIA B300-SXM-270GB | source |
| 18 | 35,435.7000 | Tokens/s | QuantaGrid D75H-10U (8x B300-SXM-270GB, TensorRT) | Quanta_Cloud_Technology | NVIDIA B300-SXM-270GB | source |