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

MLPerf v6.1 edge: NVIDIA Jetson AGX Thor 128GB agentic-edge SingleStream 1466.01 ms

1466.007675716981 ms SingleStream latency for the agentic-edge benchmark (lower is better; scenario-completion latency)

Fields

id
benchmarks/mlperf-v6-1-edge-jetson-thor-agentic-singlestream-lat
Metric
itl_ms
Value
1,466.0077
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 (NVIDIA Jetson AGX Thor Developer Kit 128G; software: TensorRT 10.16, 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. Fastest agentic-edge SingleStream in the v6.1 edge closed division.
Measured by
vendor
Reproducible
yes

Cross-references

Accelerators (1)

Engine (1)