8 × NVIDIA RTX PRO 6000 Blackwell Server Edition

Tested system

Processor: AMD EPYC 9575F
Graphics: NVIDIA RTX PRO 6000 Blackwell Server Edition
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 / gpt-oss-120bOffline · v6.1 · Tokens/s

8 × NVIDIA RTX PRO 6000 Blackwell Server Edition

15,508.40^* Tokens/s

Accuracy target / result: exact_match: 83.570
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 24.04

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

8 × NVIDIA RTX PRO 6000 Blackwell Server Edition

14,817.40^* Tokens/s

Accuracy target / result: exact_match: 84.117
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 24.04

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

8 × NVIDIA RTX PRO 6000 Blackwell Server Edition

29,904^* Tokens/s

Accuracy target / result: ROUGE1: 44.7661 ROUGE2: 22.3346 ROUGEL: 29.1319 TOKENS_PER_SAMPLE: 274.4
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 24.04

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

8 × NVIDIA RTX PRO 6000 Blackwell Server Edition

29,316.40^* Tokens/s

Accuracy target / result: ROUGE1: 44.7625 ROUGE2: 22.3336 ROUGEL: 29.1052 TOKENS_PER_SAMPLE: 273.5
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 24.04

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

8 × NVIDIA RTX PRO 6000 Blackwell Server Edition

50,453.70^* Tokens/s

Accuracy target / result: ROUGE1: 38.769 ROUGE2: 16.0147 ROUGEL: 24.5312 ROUGELSUM: 35.6942 GEN_LEN: 8178808
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 24.04

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

8 × NVIDIA RTX PRO 6000 Blackwell Server Edition

49,174.70^* Tokens/s

Accuracy target / result: ROUGE1: 38.7598 ROUGE2: 16.0015 ROUGEL: 24.5351 ROUGELSUM: 35.6872 GEN_LEN: 8179087
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 24.04

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

8 × NVIDIA RTX PRO 6000 Blackwell Server Edition

18,991.80^* Samples/s

Accuracy target / result: ACCURACY: 97.8425345223027
Weight precision: fp16
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 24.04

Processing & platform

Processor: AMD EPYC 9575F
Graphics: NVIDIA RTX PRO 6000 Blackwell Server Edition

Connectivity & software

Operating system: Ubuntu 24.04

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