HomeBenchmarks › Jetson Orin Nano 8GB
Benchmark Explorer · Jetson Orin Nano 8GB

Jetson Orin Nano 8GB: 20 benchmark rows, 35% measured.

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

7 of 20 rows are measured and published (class C); the rest are EdgeAIStack-derived (class D). 7 model families. Precisions: FP32 (2), FP16 (12), INT8 (4), INT4 (2). Runtimes: mlc (2), tensorrt (18). Tasks: text generation (2), classification (2), segmentation (2), speech recognition (3), detection (11). Jetson Orin Nano 8GB platform page.

Family × precision: best value

The fastest matching row per family and precision (fps, or tokens/s for language models), with its evidence class. Click a cell for the full breakdown.

FamilyFP32FP16INT8INT4
Llama54.8 tok/s C
MobileNet1800 fps D
MobileSAM6.8 fps C
NanoSAM37 fps C
WhisperCC
YOLO11114.8 fps D151.8 fps D
YOLOv837 fps D48 fps D

Every model on Jetson Orin Nano 8GB

Query this hardware live.

Filter by model, precision or runtime and get the matching rows with a permanent link.

OPEN BENCHMARK EXPLORER →