8 × NVIDIA GB200

Tested system

Processor: NVIDIA Grace CPU (Arm Neoverse-V2)
Graphics: NVIDIA GB200
Accelerator count: 8
Nodes: 2

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

8 × NVIDIA GB200

101,453^* Tokens/s

Accuracy target / result: exact_match: 83.727
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 144
Processors per node: 2
Nodes: 2
Total accelerators: 8
Software stack: TensorRT 10.14, CUDA 13.1, TensorRT-LLM 1.3.0rc0
Operating system: Ubuntu 24.04.4 LTS, Linux 6.14.0-37-generic-64k

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

8 × NVIDIA GB200

100,714^* Tokens/s

Accuracy target / result: exact_match: 83.485
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 144
Processors per node: 2
Nodes: 2
Total accelerators: 8
Software stack: TensorRT 10.14, CUDA 13.1, TensorRT-LLM 1.3.0rc0
Operating system: Ubuntu 24.04.4 LTS, Linux 6.14.0-37-generic-64k

Processing & platform

Processor: NVIDIA Grace CPU (Arm Neoverse-V2)
Graphics: NVIDIA GB200

Connectivity & software

Operating system: Ubuntu 24.04.4 LTS, Linux 6.14.0-37-generic-64k

System configuration

Reported host core count: 144
Processors per node: 2
Accelerator count: 8
Nodes: 2
Software stack: TensorRT 10.14, CUDA 13.1, TensorRT-LLM 1.3.0rc0
Submission division: closed

* Provisional data