8 × NVIDIA B300-SXM-270GB

Tested system

Processor: Intel(R) Xeon(R) 6776P
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

69,841.60^* Tokens/s

Accuracy target / result: exact_match: 81.58614402917047 TOKENS_PER_SAMPLE: 3773.390154968095
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-v6.0
Operating system: Rocky Linux 10.1

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

8 × NVIDIA B300-SXM-270GB

59,622.20^* Tokens/s

Accuracy target / result: exact_match: 81.17593436645396 TOKENS_PER_SAMPLE: 3821.9033728350046
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-v6.0
Operating system: Rocky Linux 10.1

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

8 × NVIDIA B300-SXM-270GB

108,293^* Tokens/s

Accuracy target / result: exact_match: 83.431
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-v6.0
Operating system: Rocky Linux 10.1

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

8 × NVIDIA B300-SXM-270GB

100,183^* Tokens/s

Accuracy target / result: exact_match: 83.451
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-v6.0
Operating system: Rocky Linux 10.1

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

8 × NVIDIA B300-SXM-270GB

113,985^* Tokens/s

Accuracy target / result: ROUGE1: 44.7969 ROUGE2: 22.3741 ROUGEL: 29.152 TOKENS_PER_SAMPLE: 272.6
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-v6.0
Operating system: Rocky Linux 10.1

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

8 × NVIDIA B300-SXM-270GB

106,285^* Tokens/s

Accuracy target / result: ROUGE1: 44.8968 ROUGE2: 22.4583 ROUGEL: 29.2397 TOKENS_PER_SAMPLE: 272.0
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-v6.0
Operating system: Rocky Linux 10.1

MLPerf Inference / whisperOffline · v6.1 · Samples/s

8 × NVIDIA B300-SXM-270GB

45,408.20^* Samples/s

Accuracy target / result: ACCURACY: 97.82350086127316
Weight precision: fp16
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-v6.0
Operating system: Rocky Linux 10.1

Processing & platform

Processor: Intel(R) Xeon(R) 6776P
Graphics: NVIDIA B300-SXM-270GB

Connectivity & software

Operating system: Rocky Linux 10.1

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-v6.0
Submission division: closed

* Provisional data