288 × NVIDIA GB300

Tested system

Processor: NVIDIA Grace CPU
Graphics: NVIDIA GB300
Accelerator count: 288
Nodes: 72

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

288 × NVIDIA GB300

2,705,130^* Tokens/s

Accuracy target / result: exact_match: 81.19872379216044 TOKENS_PER_SAMPLE: 3809.0271194165907
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 144
Processors per node: 2
Nodes: 72
Total accelerators: 288
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 24.04

679,740^* Tokens/s

Accuracy target / result: exact_match: 80.9936189608022 TOKENS_PER_SAMPLE: 3800.5963992707384
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 144
Processors per node: 2
Nodes: 18
Total accelerators: 72
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 24.04

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

288 × NVIDIA GB300

2,028,030^* Tokens/s

Accuracy target / result: exact_match: 81.13035551504102 TOKENS_PER_SAMPLE: 3861.4316317228804
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 144
Processors per node: 2
Nodes: 72
Total accelerators: 288
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 24.04

596,944^* Tokens/s

Accuracy target / result: exact_match: 81.42661804922516 TOKENS_PER_SAMPLE: 3855.550136736554
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 144
Processors per node: 2
Nodes: 18
Total accelerators: 72
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 24.04

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

288 × NVIDIA GB300

1,124,500^* Tokens/s

Accuracy target / result: exact_match: 82.861
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 144
Processors per node: 2
Nodes: 18
Total accelerators: 72
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 24.04

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

288 × NVIDIA GB300

1,120,710^* Tokens/s

Accuracy target / result: exact_match: 83.069
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 144
Processors per node: 2
Nodes: 18
Total accelerators: 72
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 24.04

Processing & platform

Processor: NVIDIA Grace CPU
Graphics: NVIDIA GB300

Connectivity & software

Operating system: Ubuntu 24.04

System configuration

Reported host core count: 144
Processors per node: 2
Accelerator count: 288
Nodes: 72
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