GeekRadar / The comparison desk
COMPARE.
Tested systems
Cisco

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

2,068.63* Tokens/s

Accuracy target / result
ROUGE1: 38.6284 ROUGE2: 15.804 ROUGEL: 24.4033 ROUGELSUM: 35.6616 GEN_LEN: 8196513
Weight precision
INT8
Division
closed
System type
datacenter
Availability
available
Cores per processor
86
Processors per node
4
Nodes
1
Total accelerators
0
Software stack
PyTorch
Operating system
Ubuntu 24.04.3
MLPerf Inference / llama3_1-8bServer · v6.1 · Tokens/s

Intel(R) Xeon(R) 6788P

1,030.45* Tokens/s

Accuracy target / result
ROUGE1: 38.8382 ROUGE2: 16.0493 ROUGEL: 24.6331 ROUGELSUM: 35.8769 GEN_LEN: 8171982
Weight precision
INT8
Division
closed
System type
datacenter
Availability
available
Cores per processor
86
Processors per node
4
Nodes
1
Total accelerators
0
Software stack
PyTorch
Operating system
Ubuntu 24.04.3
MLPerf Inference / whisperOffline · v6.1 · Samples/s

Intel(R) Xeon(R) 6788P

2,970.57* Samples/s

Accuracy target / result
ACCURACY: 97.94665880091725
Weight precision
INT8
Division
closed
System type
datacenter
Availability
available
Cores per processor
86
Processors per node
4
Nodes
1
Total accelerators
0
Software stack
PyTorch
Operating system
Ubuntu 24.04.3

Processing & platform

Processor
Intel(R) Xeon(R) 6788P

Connectivity & software

Operating system
Ubuntu 24.04.3

System configuration

Reported host core count
86
Processors per node
4
Accelerator count
0
Nodes
1
Software stack
PyTorch
Submission division
closed

* Provisional data