5 × NVIDIA RTX PRO 4500 Blackwell

Tested system

Processor: Intel(R) Xeon(R) 6787P
Graphics: NVIDIA RTX PRO 4500 Blackwell
Accelerator count: 5
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 / llama3.1-8bOffline · v6.1 · Tokens/s

5 × NVIDIA RTX PRO 4500 Blackwell

12,017.70^* Tokens/s

Accuracy target / result: ROUGE1: 38.7698 ROUGE2: 16.0132 ROUGEL: 24.5304 ROUGELSUM: 35.6924 GEN_LEN: 8178850
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 86
Processors per node: 2
Nodes: 1
Total accelerators: 5
Software stack: TensorRT 10.14, CUDA 13.1
Operating system: Ubuntu 24.04

MLPerf Inference / llama3.1-8bServer · v6.1 · Tokens/s

5 × NVIDIA RTX PRO 4500 Blackwell

11,426.10^* Tokens/s

Accuracy target / result: ROUGE1: 38.7615 ROUGE2: 16.0056 ROUGEL: 24.5235 ROUGELSUM: 35.6866 GEN_LEN: 8178120
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 86
Processors per node: 2
Nodes: 1
Total accelerators: 5
Software stack: TensorRT 10.14, CUDA 13.1
Operating system: Ubuntu 24.04

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

5 × NVIDIA RTX PRO 4500 Blackwell

4,808.98^* Samples/s

Accuracy target / result: ACCURACY: 97.83682442399383
Weight precision: fp16
Division: closed
System type: datacenter
Availability: available
Cores per processor: 86
Processors per node: 2
Nodes: 1
Total accelerators: 5
Software stack: TensorRT 10.14, CUDA 13.1
Operating system: Ubuntu 24.04

Processing & platform

Processor: Intel(R) Xeon(R) 6787P
Graphics: NVIDIA RTX PRO 4500 Blackwell

Connectivity & software

Operating system: Ubuntu 24.04

System configuration

Reported host core count: 86
Processors per node: 2
Accelerator count: 5
Nodes: 1
Software stack: TensorRT 10.14, CUDA 13.1
Submission division: closed

* Provisional data