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

MLPerf v6.1 edge: AMD Strix Halo (Ryzen AI Max+ 395 / 8060S) agentic-edge SingleStream 7058.99 ms

7058.989199685204 ms SingleStream latency for the agentic-edge benchmark (lower is better; scenario-completion latency)

Fields

id
benchmarks/mlperf-v6-1-edge-strix-halo-8060s-agentic-singlestream-lat
Metric
itl_ms
Value
7,058.9892
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 (Atlas_Inference, AMD Strix Halo desktop; software: Atlas (spark), native-HIP NVFP4). 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.
Measured by
vendor
Reproducible
yes

Cross-references

Accelerators (2)

Engine (1)