4 × NVIDIA GB200

Tested system

Processor: NVIDIA Grace CPU
Graphics: NVIDIA GB200
Accelerator count: 4
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 / gpt-oss-120bOffline · v6.1 · Tokens/s

4 × NVIDIA GB200

50,912.90^* Tokens/s

Accuracy target / result: exact_match: 83.691
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 144
Processors per node: 2
Nodes: 1
Total accelerators: 4
Software stack: TensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf
Operating system: Ubuntu 24.04

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

4 × NVIDIA GB200

50,613.50^* Tokens/s

Accuracy target / result: exact_match: 83.642
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 144
Processors per node: 2
Nodes: 1
Total accelerators: 4
Software stack: TensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf
Operating system: Ubuntu 24.04

Processing & platform

Processor: NVIDIA Grace CPU
Graphics: NVIDIA GB200

Connectivity & software

Operating system: Ubuntu 24.04

System configuration

Reported host core count: 144
Processors per node: 2
Accelerator count: 4
Nodes: 1
Software stack: TensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf
Submission division: closed

* Provisional data