8 × NVIDIA B200-SXM-180GB

Tested system

Processor: Intel(R) Xeon(R) Platinum 8580
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

56,929.90^* Tokens/s

Accuracy target / result: exact_match: 81.08477666362808 TOKENS_PER_SAMPLE: 3808.5396536007293
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 60
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: TensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentML:mlperf-inf-mm-q3vl-v6.0
Operating system: Ubuntu 24.04.3 LTS (Linux kernel: 6.11.0-1016-nvidia #16-Ubuntu SMP PREEMPT_DYNAMIC Sun Sep 21 17:06:33 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux)

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

8 × NVIDIA B200-SXM-180GB

55,869^* Tokens/s

Accuracy target / result: exact_match: 80.62898814949864 TOKENS_PER_SAMPLE: 3840.4710574293526
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 60
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: TensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentML:mlperf-inf-mm-q3vl-v6.0
Operating system: Ubuntu 24.04.3 LTS (Linux kernel: 6.11.0-1016-nvidia #16-Ubuntu SMP PREEMPT_DYNAMIC Sun Sep 21 17:06:33 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux)

MLPerf Inference / gpt-oss-120bOffline · v6.1 · Tokens/s

8 × NVIDIA B200-SXM-180GB

88,491^* Tokens/s

Accuracy target / result: exact_match: 83.040
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 60
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: TensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentML:mlperf-inf-mm-q3vl-v6.0
Operating system: Ubuntu 24.04.3 LTS (Linux kernel: 6.11.0-1016-nvidia #16-Ubuntu SMP PREEMPT_DYNAMIC Sun Sep 21 17:06:33 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux)

MLPerf Inference / gpt-oss-120bServer · v6.1 · Tokens/s

8 × NVIDIA B200-SXM-180GB

89,856.30^* Tokens/s

Accuracy target / result: exact_match: 82.998
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 60
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: TensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentML:mlperf-inf-mm-q3vl-v6.0
Operating system: Ubuntu 24.04.3 LTS (Linux kernel: 6.11.0-1016-nvidia #16-Ubuntu SMP PREEMPT_DYNAMIC Sun Sep 21 17:06:33 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux)

Processing & platform

Processor: Intel(R) Xeon(R) Platinum 8580
Graphics: NVIDIA B200-SXM-180GB

Connectivity & software

Operating system: Ubuntu 24.04.3 LTS (Linux kernel: 6.11.0-1016-nvidia #16-Ubuntu SMP PREEMPT_DYNAMIC Sun Sep 21 17:06:33 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux)

System configuration

Reported host core count: 60
Processors per node: 2
Accelerator count: 8
Nodes: 1
Software stack: TensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentML:mlperf-inf-mm-q3vl-v6.0
Submission division: closed

* Provisional data