8 × NVIDIA B300-SXM-270GB

Tested system

Processor: AMD EPYC 9575F
Graphics: NVIDIA B300-SXM-270GB
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 B300-SXM-270GB

72,327.10^* Tokens/s

Accuracy target / result: exact_match: 80.9936189608022 TOKENS_PER_SAMPLE: 3803.4314038286234
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 64
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-v6.1
Operating system: Ubuntu 22.04.4

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

8 × NVIDIA B300-SXM-270GB

70,771.70^* Tokens/s

Accuracy target / result: exact_match: 80.76572470373746 TOKENS_PER_SAMPLE: 3851.8625797629898
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 64
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-v6.1
Operating system: Ubuntu 22.04.4

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

8 × NVIDIA B300-SXM-270GB

111,541^* Tokens/s

Accuracy target / result: exact_match: 82.928
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 64
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-v6.1
Operating system: Ubuntu 22.04.4

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

8 × NVIDIA B300-SXM-270GB

110,592^* Tokens/s

Accuracy target / result: exact_match: 83.965
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 64
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-v6.1
Operating system: Ubuntu 22.04.4

MLPerf Inference / llama2-70b-99.9Offline · v6.1 · Tokens/s

8 × NVIDIA B300-SXM-270GB

114,826^* Tokens/s

Accuracy target / result: ROUGE1: 44.8002 ROUGE2: 22.3763 ROUGEL: 29.1593 TOKENS_PER_SAMPLE: 272.5
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 64
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-v6.1
Operating system: Ubuntu 22.04.4

MLPerf Inference / llama2-70b-99.9Server · v6.1 · Tokens/s

8 × NVIDIA B300-SXM-270GB

114,578^* Tokens/s

Accuracy target / result: ROUGE1: 44.8817 ROUGE2: 22.4296 ROUGEL: 29.2316 TOKENS_PER_SAMPLE: 271.9
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 64
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-v6.1
Operating system: Ubuntu 22.04.4

Processing & platform

Processor: AMD EPYC 9575F
Graphics: NVIDIA B300-SXM-270GB

Connectivity & software

Operating system: Ubuntu 22.04.4

System configuration

Reported host core count: 64
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-v6.1
Submission division: closed

* Provisional data