Cisco · Cisco UCS X215c M8 - X580P PCIe Node (4x RTXPro6000-PCIe-96GB, TensorRT)
Llama-3.1-8B (MLPerf reference) · llama3.1-8b · Server · run 01a00b49-c116…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported23,423.9 tokens_s
Llama-3.1-8B (MLPerf reference) · llama3.1-8b · Server · server · 4× NVIDIA RTX PRO 6000 Blackwell Server Edition · mlperf_closed_99 · observed 2026-03-26
Identity
modelLlama-3.1-8B (MLPerf reference)
stackTensorRT 10.11, CUDA 12.9
workloadllama3.1-8b · Server
topology4× NVIDIA RTX PRO 6000 Blackwell Server Edition
harnessmlperf_loadgen v6.0
quality policymlperf_closed_99
comparison keysha256:54245202f74d4a49…
sha256:dbc69de5b6379f652b03634…
Launch configuration
dtypefp4
notesNVIDIA RTX PRO 6000 Blackwell Server Edition TGP 600W
systemCisco UCS X215c M8 - X580P PCIe Node (4x RTXPro6000-PCIe-96GB, TensorRT)
softwareTensorRT 10.11, CUDA 12.9
availabilityavailable
Workload
namellama3.1-8b · 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 RTX PRO 6000 Blackwell Server Edition",
"acceleratorVendor": "nvidia",
"acceleratorsPerNode": 4
},
"observedAt": "2026-03-26T19:39:54Z",
"modelDigest": "sha256:dafdb8bb411a12b698d36856eed69f16242fb467999fb68680ca09a5601b6bd4",
"measurements": [
{
"unit": "tokens_s",
"value": 23423.9,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 23423.9
},
"category": "datacenter",
"division": "closed",
"scenario": "server",
"benchmark": "llama3.1-8b",
"externalId": "v6.0/6.0-0014"
},
"qualityPolicy": "mlperf_closed_99",
"workloadDigest": "sha256:209ab3ba41ef397171c081377f84bcb2512e3d47cd6334278a712a3858d8eedd",
"configurationDigest": "sha256:db8bf778a1e89d15823b292a8021cc5864a2f21ff82437f57c69622be893984e"
},
"metadata": {
"name": "mlperf-v6-0-6-0-0014",
"title": "Cisco · llama3.1-8b · Server",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/submissions_inference_v6.0/tree/main/closed/Cisco/results/X215M8_X580P_RTXPro6000_96GBx4_TRT"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v6.0/6.0-0014 · shown unmodified as publishedAll serving results →JSON