HPE · HPE ProLiant Compute XD685 (8x NVIDIA B200 180GB, TensorRT)
Mixtral-8x7B (MLPerf reference) · mixtral-8x7b · Server · run 01a00b49-fb22…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported127,209 tokens_s
Mixtral-8x7B (MLPerf reference) · mixtral-8x7b · Server · server · 8× NVIDIA B200-SXM-180GB · mlperf_closed_99 · observed 2026-03-26
Identity
modelMixtral-8x7B (MLPerf reference)
stackTensorRT 10.11, CUDA 13.0
workloadmixtral-8x7b · Server
topology8× NVIDIA B200-SXM-180GB
harnessmlperf_loadgen v6.0
quality policymlperf_closed_99
comparison keysha256:d582681c75874649…
sha256:cf8260586c75c286894c400…
Launch configuration
dtypefp4
notesB200 TGP 1000W
systemHPE ProLiant Compute XD685 (8x NVIDIA B200 180GB, TensorRT)
softwareTensorRT 10.11, CUDA 13.0
availabilityavailable
Workload
namemixtral-8x7b · 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 B200-SXM-180GB",
"acceleratorVendor": "nvidia",
"acceleratorsPerNode": 8
},
"observedAt": "2026-03-26T19:39:54Z",
"modelDigest": "sha256:80245861fefd582d681d995dd4a278c0f97669415a5a9ee66bcab60e81a11738",
"measurements": [
{
"unit": "tokens_s",
"value": 127209,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 127209
},
"category": "datacenter",
"division": "closed",
"scenario": "server",
"benchmark": "mixtral-8x7b",
"externalId": "v6.0/6.0-0048"
},
"qualityPolicy": "mlperf_closed_99",
"workloadDigest": "sha256:cf6f6283cf16bb894b6829de78b6756e83e48e010ba0a999e170326678bdab2f",
"configurationDigest": "sha256:62b388501f3814d086d191e32d93398354ee179c535299fe91c55134153dd3f9"
},
"metadata": {
"name": "mlperf-v6-0-6-0-0048",
"title": "HPE · mixtral-8x7b · Server",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/submissions_inference_v6.0/tree/main/closed/HPE/results/HPE_ProLiant_XD685_B200_SXM_192GBx8_TRT"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v6.0/6.0-0048 · shown unmodified as publishedAll serving results →JSON