MLPerf v6.1 edge OPEN: HPE DL345 4x RTX PRO 4500 PCIe 32GB llama3.1-8b-edge SingleStream 1203.79 ms
1203.785699 ms SingleStream latency for the agentic-edge benchmark (lower is better; scenario-completion latency)
Fields
id
benchmarks/mlperf-v6-1-edgeopen-rtxpro4500-4x-llama31-8b-singlestream-latMetric
itl_ms
Value
1,203.7857
Unit
ms SingleStream latency for the agentic-edge benchmark (lower is better; scenario-completion latency)
Model
MLPerf 'agentic edge' workload
Methodology
MLPerf Inference v6.1 EDGE closed submission (HPE ProLiant DL345 Gen12, 4x RTX PRO 4500-PCIe-32GB (open division); software: TensorRT 10.15.1.29, CUDA 13.2). SingleStream latency in ms for the 'agentic edge' benchmark - this is a LATENCY result, not throughput; recorded under itl_ms as the only ms-latency member of the metric enum that fits a per-request latency measure. Open division; model = llama3.1-8b-edge.
Measured by
vendor
Reproducible
yes