inference/research
verifiedmedium · 0.70updated 2026-10-15

MLPerf v6.1 edge: HPE DL145 1x RTX PRO 4500 SE 32GB agentic-edge SingleStream 2757.95 ms

2757.954404037736 ms SingleStream latency for the agentic-edge benchmark (lower is better; scenario-completion latency)

Fields

id
benchmarks/mlperf-v6-1-edge-rtxpro4500-1x-agentic-singlestream-lat
Metric
itl_ms
Value
2,757.9544
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 DL145 Gen11, 1x RTX PRO 4500 SE 32GB; software: llama.cpp). 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. Notable: an llama.cpp submission inside MLPerf closed division - rare.
Measured by
vendor
Reproducible
yes

Cross-references