GeekRadar / The comparison desk
COMPARE.
Tested systems
CoreWeave

72 × NVIDIA GB300

Tested system

Processor
NVIDIA Grace (Neoverse-V2)
Graphics
NVIDIA GB300
Accelerator count
72
Nodes
18

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

72 × NVIDIA GB300

1,197,710* Tokens/s

Accuracy target / result
exact_match: 83.098
Weight precision
fp4
Division
closed
System type
datacenter
Availability
available
Cores per processor
72
Processors per node
2
Nodes
18
Total accelerators
72
Software stack
TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentML:mlperf-inf-mm-q3vl-v6.0
Operating system
Ubuntu 24.04
MLPerf Inference / gpt-oss-120bServer · v6.1 · Tokens/s

72 × NVIDIA GB300

1,160,490* Tokens/s

Accuracy target / result
exact_match: 82.875
Weight precision
fp4
Division
closed
System type
datacenter
Availability
available
Cores per processor
72
Processors per node
2
Nodes
18
Total accelerators
72
Software stack
TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentML:mlperf-inf-mm-q3vl-v6.0
Operating system
Ubuntu 24.04
MLPerf Inference / llama2-70b-99.9Offline · v6.1 · Tokens/s

72 × NVIDIA GB300

1,136,100* Tokens/s

Accuracy target / result
ROUGE1: 44.8147 ROUGE2: 22.3736 ROUGEL: 29.189 TOKENS_PER_SAMPLE: 272.4
Weight precision
fp4
Division
closed
System type
datacenter
Availability
available
Cores per processor
72
Processors per node
2
Nodes
18
Total accelerators
72
Software stack
TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentML:mlperf-inf-mm-q3vl-v6.0
Operating system
Ubuntu 24.04
MLPerf Inference / llama2-70b-99.9Server · v6.1 · Tokens/s

72 × NVIDIA GB300

944,902* Tokens/s

Accuracy target / result
ROUGE1: 44.8524 ROUGE2: 22.4096 ROUGEL: 29.218 TOKENS_PER_SAMPLE: 272.3
Weight precision
fp4
Division
closed
System type
datacenter
Availability
available
Cores per processor
72
Processors per node
2
Nodes
18
Total accelerators
72
Software stack
TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentML:mlperf-inf-mm-q3vl-v6.0
Operating system
Ubuntu 24.04

Processing & platform

Processor
NVIDIA Grace (Neoverse-V2)
Graphics
NVIDIA GB300

Connectivity & software

Operating system
Ubuntu 24.04

System configuration

Reported host core count
72
Processors per node
2
Accelerator count
72
Nodes
18
Software stack
TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentML:mlperf-inf-mm-q3vl-v6.0
Submission division
closed

* Provisional data