llama3.1-8b · Interactive
llama3.1-8b / Interactive / Tokens/s
v6.0|closed|llama3.1-8b|Interactive|Tokens/s|official-system
Metric: Performance_Result (Tokens/s) · winning: higher · 10 ranking-eligible rows · vendors 1 · families 3 · never mixed with other slices
All systems (official)
| Rank | Performance | Unit | System | Submitter | Accelerator | Source |
|---|---|---|---|---|---|---|
| 1 | 128,750.0000 | Tokens/s | NVIDIA DGX B200 (8x B200-SXM-180GB, TensorRT) | Lambda_SIT | NVIDIA B200-SXM-180GB | source |
| 2 | 128,633.0000 | Tokens/s | G894-SD3-AAX7 | GigaComputing | NVIDIA B300-SXM-270GB | source |
| 3 | 126,143.0000 | Tokens/s | HPE ProLiant Compute XD685 (8x NVIDIA B200 180GB, TensorRT) | HPE | NVIDIA B200-SXM-180GB | source |
| 4 | 53,054.7000 | 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 |
| 5 | 44,087.3000 | 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 |
| 6 | 34,241.0000 | Tokens/s | ESC8000A_E13P_RTX_PRO_6000_PCIE_96GBx8 | ASUSTeK | NVIDIA RTX PRO 6000 Blackwell Server Edition | source |
| 7 | 20,118.9000 | 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 |
| 8 | 19,991.1000 | 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 |
| 9 | 10,589.3000 | 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 |
| 10 | 10,459.6000 | 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 |