Quanta_Cloud_Technology · QuantaGrid D75H-10U (8x B300-SXM-270GB, TensorRT)
Llama-3.1-405B (MLPerf reference) · llama3.1-405b · Server · run 01a00b4a-40c5…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported1,484.4 tokens_s
Llama-3.1-405B (MLPerf reference) · llama3.1-405b · Server · server · 8× NVIDIA B300-SXM-270GB · mlperf_closed_99 · observed 2026-03-26
Identity
modelLlama-3.1-405B (MLPerf reference)
stackTensorRT 10.14, CUDA 13.1
workloadllama3.1-405b · Server
topology8× NVIDIA B300-SXM-270GB
harnessmlperf_loadgen v6.0
quality policymlperf_closed_99
comparison keysha256:f8a1f44fd18bc886…
sha256:73fdd5a21793f9c758ce5ab…
Launch configuration
dtypefp4
notesB300 TGP 1100W
systemQuantaGrid D75H-10U (8x B300-SXM-270GB, TensorRT)
softwareTensorRT 10.14, CUDA 13.1
availabilityavailable
Workload
namellama3.1-405b · Server
streamingyes
load generationopen_loop
Canonical manifest
Show manifestHide manifest
{
"kind": "ServingRun",
"spec": {
"status": "valid",
"harness": {
"name": "mlperf_loadgen",
"version": "v6.0"
},
"topology": {
"nodeCount": 1,
"acceleratorModel": "NVIDIA B300-SXM-270GB",
"acceleratorVendor": "nvidia",
"acceleratorsPerNode": 8
},
"observedAt": "2026-03-26T19:39:54Z",
"modelDigest": "sha256:bc69ffe83643f1c91a137a177c5ef85829a1f5b65ae51771adb75ef783baf031",
"measurements": [
{
"unit": "tokens_s",
"value": 1484.4,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 1484.4
},
"category": "datacenter",
"division": "closed",
"scenario": "server",
"benchmark": "llama3.1-405b",
"externalId": "v6.0/6.0-0089"
},
"qualityPolicy": "mlperf_closed_99",
"workloadDigest": "sha256:3428d964054278646d17c2f6064b4e29982b970b7fa607362cf50b7f7dff994c",
"configurationDigest": "sha256:406a519b044aa6a3840201ede7905317e2fd1ca8708459f77d49b6d044b3960f"
},
"metadata": {
"name": "mlperf-v6-0-6-0-0089",
"title": "Quanta_Cloud_Technology · llama3.1-405b · Server",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/submissions_inference_v6.0/tree/main/closed/Quanta_Cloud_Technology/results/D75H-10U_B300-270GBx8_TRT"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v6.0/6.0-0089 · shown unmodified as publishedAll serving results →JSON