HomeBenchmarksJetson Orin Nano 8GB › MobileNetv2
Benchmark Explorer · MobileNetv2 on Jetson Orin Nano 8GB

MobileNetv2 on Jetson Orin Nano 8GB: 1 row.

Method v1.0 · dataset 2026-09-07 · verified 2026-09-07 · last updated September 2026

mobilenetv2 on Jetson Orin Nano 8GB: 1 row (0 measured, 1 derived). Expected: FP16 1800 fps. Fastest: Jetson Orin Nano 8GB 1800 fps (class D), Hailo-8 1100 fps (class C), Hailo-8L 550 fps (class C).

Change hardware, precision, runtime or add a comparison set on the live engine.

Expected range per precision

Min / median / max of the matching rows, all classes. When a precision has no row, the estimator's benchmark hierarchy (B → C → D) supplies a fallback with its tier chain reported.

PrecisionMetricNMinMedianMaxBest classMeasured
FP16fps1180018001800D0

Rows

PrecisionRuntimeInputPower modeSoftwareMetricClassDateSourceDerivationDupes
FP16tensorrt (inferred)224x224 b1default1800 fpsD2024-Q1EdgeAIStack · edgeaistack:benchmark-corpus · Estimated from NVIDIA Jetson Xavier NX SSD-MobileNetV1 benchmark (887 FPS) scaled to MobileNetV2 complexity and Orin Nan · verified 2026-09-07Estimated from NVIDIA Jetson Xavier NX SSD-MobileNetV1 benchmark (887 FPS) scaled to MobileNetV2 complexity and Orin Nano GPU0

Cross-hardware comparison

Best row per hardware for the same model and precision, relative to the fastest.

HardwareBest valueClass
Jetson Orin Nano 8GB1800 fps
D
Hailo-81100 fps
C
Hailo-8L550 fps
C
Google Coral Edge TPU385 fps
C

Assumptions

  • Rows from the research corpus do not state a runtime; the platform's native runtime (TensorRT / Edge TPU / Hailo SDK / RKNN / CPU) is assumed and flagged runtime_inferred.
  • Class C = measured and published by the source named on the row; class D = EdgeAIStack-derived (derivation stated). Rows are inference-only unless scope says end_to_end; publisher measurement conditions (JetPack, batch, warm-up) are in the linked page.

Warnings

  • 1 of 1 matching rows are EdgeAIStack-derived (class D); treat them as estimates until a measured row (class C) or your own measurement replaces them.

Method and limitations

Rows are read from the normalised benchmark database (publisher benchmarks and research-derived rows, deduplicated per hardware × model × runtime × precision × input × power mode, best evidence kept). Expected range = min / median / max of the matching rows per precision; when a precision has no row the estimator's benchmark hierarchy (B → C → D) is consulted and its tier chain reported. Comparison = best row per hardware for the same model and precision, relative to the fastest. Nothing is scored; every number carries its class and source line.

Full method, dedupe rule, evidence classes and the confidence rule: Benchmark Explorer methodology.

Measure it yourself.

Nothing measured for your exact config, or want to confirm a class-D row? Run the measurement protocol on your board and submit the result — a human checks it against the protocol before it becomes a class-C row with your attribution.

SUBMIT A MEASUREMENT →

Change one input and re-run.

The live engine keeps every source line and gives you a fresh permalink and summary.

OPEN THIS QUERY LIVE →