Intel(R) Xeon(R) 6788P

Tested system

Processor: Intel(R) Xeon(R) 6788P
Accelerator count: 0
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

Intel(R) Xeon(R) 6788P

1,170.51^* Tokens/s

Accuracy target / result: ROUGE1: 38.703 ROUGE2: 15.9823 ROUGEL: 24.5421 ROUGELSUM: 35.7696 GEN_LEN: 8188918
Weight precision: INT8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 86
Processors per node: 2
Nodes: 1
Total accelerators: 0
Software stack: PyTorch
Operating system: Ubuntu 25.10

MLPerf Inference / llama3_1-8bServer · v6.1 · Tokens/s

Intel(R) Xeon(R) 6788P

516.01^* Tokens/s

Accuracy target / result: ROUGE1: 38.6189 ROUGE2: 15.8198 ROUGEL: 24.4192 ROUGELSUM: 35.6324 GEN_LEN: 8192507
Weight precision: INT8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 86
Processors per node: 2
Nodes: 1
Total accelerators: 0
Software stack: PyTorch
Operating system: Ubuntu 25.10

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

Intel(R) Xeon(R) 6788P

15,633.30^* Samples/s

Accuracy target / result: acc: 71.489
Weight precision: INT8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 86
Processors per node: 2
Nodes: 1
Total accelerators: 0
Software stack: PyTorch
Operating system: Ubuntu 25.10

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

Intel(R) Xeon(R) 6788P

1,548.10^* Samples/s

Accuracy target / result: ACCURACY: 97.89045996917045
Weight precision: INT8
Division: closed
System type: datacenter
Availability: available
Cores per processor: 86
Processors per node: 2
Nodes: 1
Total accelerators: 0
Software stack: PyTorch
Operating system: Ubuntu 25.10

Processing & platform

Processor: Intel(R) Xeon(R) 6788P

Connectivity & software

Operating system: Ubuntu 25.10

System configuration

Reported host core count: 86
Processors per node: 2
Accelerator count: 0
Nodes: 1
Software stack: PyTorch
Submission division: closed

* Provisional data