8 × NVIDIA B200-SXM-180GB

Tested system

Processor: Intel(R) Xeon(R) 6767P
Graphics: NVIDIA B200-SXM-180GB
Accelerator count: 8
Nodes: 1

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

MLPerf Inference / deepseek-r1Offline · v6.1 · Tokens/s

8 × NVIDIA B200-SXM-180GB

60,410.90^* Tokens/s

Accuracy target / result: exact_match: 81.70009115770283 TOKENS_PER_SAMPLE: 3727.5230173199634
Weight precision: fp4
Division: open
System type: datacenter
Availability: available
Cores per processor: 64
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: TensorRT-LLM 1.3.0rc0, CUDA 13.1
Operating system: Ubuntu 24.04.3 LTS

MLPerf Inference / deepseek-r1Server · v6.1 · Tokens/s

8 × NVIDIA B200-SXM-180GB

59,668.30^* Tokens/s

Accuracy target / result: exact_match: 81.17593436645396 TOKENS_PER_SAMPLE: 3739.3393345487693
Weight precision: fp4
Division: open
System type: datacenter
Availability: available
Cores per processor: 64
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: TensorRT-LLM 1.3.0rc0, CUDA 13.1
Operating system: Ubuntu 24.04.3 LTS

Processing & platform

Processor: Intel(R) Xeon(R) 6767P
Graphics: NVIDIA B200-SXM-180GB

Connectivity & software

Operating system: Ubuntu 24.04.3 LTS

System configuration

Reported host core count: 64
Processors per node: 2
Accelerator count: 8
Nodes: 1
Software stack: TensorRT-LLM 1.3.0rc0, CUDA 13.1
Submission division: open

* Provisional data