llama3.1-8b · Offline
llama3.1-8b / Offline / Tokens/s
v6.0|closed|llama3.1-8b|Offline|Tokens/s|official-system
Metric: Performance_Result (Tokens/s) · winning: higher · 23 ranking-eligible rows · vendors 2 · families 8 · never mixed with other slices
All systems (official)
| Rank | Performance | Unit | System | Submitter | Accelerator | Source |
|---|---|---|---|---|---|---|
| 1 | 166,745.0000 | Tokens/s | XA NB3I-E12 | ASUSTeK | NVIDIA B300-SXM-270GB | source |
| 2 | 165,432.0000 | Tokens/s | NVIDIA DGX B300 (8x B300-SXM-270GB, TensorRT) | NVIDIA | NVIDIA B300-SXM-270GB | source |
| 3 | 160,403.0000 | Tokens/s | NVIDIA DGX B200 (8x B200-SXM-180GB, TensorRT) | Lambda_SIT | NVIDIA B200-SXM-180GB | source |
| 4 | 152,625.0000 | Tokens/s | HPE ProLiant Compute XD685 (8x NVIDIA B200 180GB, TensorRT) | HPE | NVIDIA B200-SXM-180GB | source |
| 5 | 150,707.0000 | Tokens/s | G894-SD3-AAX7 | GigaComputing | NVIDIA B300-SXM-270GB | source |
| 6 | 60,679.9000 | Tokens/s | HPE ProLiant Compute DL380a Gen12 (10x NVIDIA RTX PRO 6000 Blackwell Server Edition, TensorRT) | HPE | NVIDIA RTX PRO 6000 Blackwell Server Edition | source |
| 7 | 53,193.6000 | Tokens/s | PowerEdge XE7740 (8x H200-NVL-141GB, TensorRT) | Dell | NVIDIA H200-NVL-141GB | source |
| 8 | 49,580.2000 | Tokens/s | HPE ProLiant Compute DL380a Gen12 (8x NVIDIA RTX PRO 6000 Blackwell Server Edition, TensorRT) | HPE | NVIDIA RTX PRO 6000 Blackwell Server Edition | source |
| 9 | 49,036.1000 | Tokens/s | PowerEdge XE7745 (8x RTXPro6000-PCIe-96GB, TensorRT) | Dell | NVIDIA RTX PRO 6000 Blackwell Server Edition | source |
| 10 | 48,791.0000 | Tokens/s | ESC8000A_E13P_RTX_PRO_6000_PCIE_96GBx8 | ASUSTeK | NVIDIA RTX PRO 6000 Blackwell Server Edition | source |
| 11 | 48,613.8000 | Tokens/s | ESC8000_E12P_RTX_PRO_6000_PCIE_96GBx8 | ASUSTeK | NVIDIA RTX PRO 6000 Blackwell Server Edition | source |
| 12 | 24,216.6000 | Tokens/s | Cisco UCS X210 M8 - X580P PCIe Node (4x H200-NVL-141GB, TensorRT) | Cisco | NVIDIA H200-NVL-141GB | source |
| 13 | 24,013.5000 | Tokens/s | Cisco UCS X215c M8 - X580P PCIe Node (4x RTXPro6000-PCIe-96GB, TensorRT) | Cisco | NVIDIA RTX PRO 6000 Blackwell Server Edition | source |
| 14 | 23,556.7000 | Tokens/s | HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition-450W, TensorRT) | HPE | NVIDIA RTX PRO 6000 Blackwell Server Edition | source |
| 15 | 23,265.7000 | Tokens/s | HPE ProLiant DL385 Gen11 (4x NVIDIA RTX PRO 6000 Blackwell Server Edition-450W, TensorRT) | HPE | NVIDIA RTX PRO 6000 Blackwell Server Edition | source |
| 16 | 12,495.2000 | Tokens/s | HPE ProLiant DL385 Gen11 (2x NVIDIA RTX PRO 6000 Blackwell Server Edition-600W, TensorRT) | HPE | NVIDIA RTX PRO 6000 Blackwell Server Edition | source |
| 17 | 12,433.3000 | Tokens/s | HPE ProLiant DL385 Gen11 (2x NVIDIA RTX PRO 6000 Blackwell Server Edition-600W, TensorRT) | HPE | NVIDIA RTX PRO 6000 Blackwell Server Edition | source |
| 18 | 11,665.0000 | Tokens/s | HPE ProLiant Compute DL380 Gen12 (5x NVIDIA RTX PRO 4500 Blackwell, TensorRT) | HPE | NVIDIA RTX PRO 4500 Blackwell | source |
| 19 | 6,762.3000 | Tokens/s | 1-node-4x-BMG-Pro-B60-Dual | Intel | MS-Intel Arc Pro B60 Dual 48G Turbo | source |
| 20 | 4,617.4000 | Tokens/s | 1-node-4x-BMG-B70 | Intel | Intel(R) Arc Pro(R) B70 | source |
| 21 | 3,347.4300 | Tokens/s | 1-node-4x-BMG-B60 | Intel | Intel(R) Arc Pro(R) B60 | source |
| 22 | 2,340.7500 | Tokens/s | HPE ProLiant DL145 Gen11 (1x NVIDIA RTX PRO 4500 Blackwell, TensorRT) | HPE | NVIDIA RTX PRO 4500 Blackwell | source |
| 23 | 1,721.8400 | Tokens/s | 1-node-4x-BMG-B50 | Intel | Intel(R) Arc Pro(R) B50 | source |