8 × NVIDIA B300-SXM-270GB

Tested system

Processor: Intel(R) Xeon(R) 6767P
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

69,846.90^* Tokens/s

Accuracy target / result: exact_match: 80.76572470373746 TOKENS_PER_SAMPLE: 3759.735870556062
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
Operating system: Ubuntu 22.04

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

8 × NVIDIA B300-SXM-270GB

54,568.60^* Tokens/s

Accuracy target / result: exact_match: 80.9024612579763 TOKENS_PER_SAMPLE: 3802.827256153145
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
Operating system: Ubuntu 22.04

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

8 × NVIDIA B300-SXM-270GB

109,368^* Tokens/s

Accuracy target / result: exact_match: 83.572
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
Operating system: Ubuntu 22.04

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

8 × NVIDIA B300-SXM-270GB

109,949^* Tokens/s

Accuracy target / result: exact_match: 83.403
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
Operating system: Ubuntu 22.04

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

8 × NVIDIA B300-SXM-270GB

113,007^* Tokens/s

Accuracy target / result: ROUGE1: 44.7974 ROUGE2: 22.3739 ROUGEL: 29.1541 TOKENS_PER_SAMPLE: 272.7
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
Operating system: Ubuntu 22.04

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

8 × NVIDIA B300-SXM-270GB

113,455^* Tokens/s

Accuracy target / result: ROUGE1: 44.8853 ROUGE2: 22.409 ROUGEL: 29.2169 TOKENS_PER_SAMPLE: 272.2
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
Operating system: Ubuntu 22.04

Processing & platform

Processor: Intel(R) Xeon(R) 6767P
Graphics: NVIDIA B300-SXM-270GB

Connectivity & software

Operating system: Ubuntu 22.04

System configuration

Reported host core count: 64
Processors per node: 2
Accelerator count: 8
Nodes: 1
Software stack: TensorRT 10.14, CUDA 13.1
Submission division: closed

* Provisional data