GeekRadar / The comparison desk
COMPARE.
Tested systems
Cisco

8 × NVIDIA B300-SXM-270GB

Tested system

Processor
Intel(R) Xeon(R) 6767P
Graphics
NVIDIA B300-SXM-270GB
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 / deepseek-r1Offline · v6.1 · Tokens/s

8 × NVIDIA B300-SXM-270GB

70,325.40* Tokens/s

Accuracy target / result
exact_match: 80.92525068368278 TOKENS_PER_SAMPLE: 3782.986326344576
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 / deepseek-r1Server · v6.1 · Tokens/s

8 × NVIDIA B300-SXM-270GB

66,171.60* Tokens/s

Accuracy target / result
exact_match: 80.76572470373746 TOKENS_PER_SAMPLE: 3811.0783956244304
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 B300-SXM-270GB

171,114* Tokens/s

Accuracy target / result
ROUGE1: 38.4898 ROUGE2: 15.9329 ROUGEL: 24.3413 ROUGELSUM: 35.6705 GEN_LEN: 8186559
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 B300-SXM-270GB

173,950* Tokens/s

Accuracy target / result
ROUGE1: 38.4912 ROUGE2: 15.9156 ROUGEL: 24.3266 ROUGELSUM: 35.6593 GEN_LEN: 8186471
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 B300-SXM-270GB

52,221.80* Samples/s

Accuracy target / result
ACCURACY: 97.8263559104276
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
Intel(R) Xeon(R) 6767P
Graphics
NVIDIA B300-SXM-270GB

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