Home › Benchmarks › Hailo-10H
Benchmark Explorer · Hailo-10H

Hailo-10H: 36 benchmark rows, 44% measured.

Method v1.4.1 · dataset 2026-09-29 · verified 2026-09-16 · last updated September 2026

16 of 36 rows are measured and published (class C); the rest are EdgeAIStack-derived (class D). 12 model families. Precisions: INT8 (36). Runtimes: hailo sdk (36). Tasks: detection (25), classification (2), segmentation (7), pose (2).

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.

FamilyINT8
CenterNet240 fps D
MobileNet2864 fps D
MobileNetV22944 fps D
ResNet316 fps D
SSD MobileNet501 fps D
YOLO11332 fps C
YOLOv10345 fps C
YOLOv5296 fps C
YOLOv5249 fps D
YOLOv8375 fps C
YOLOv8161 fps D
YOLOv8310 fps D

Every model on Hailo-10H

CenterNet Resnet18
CenterNet · resnet18
MobileNetv1
MobileNet · v1
MobileNetV2v2
MobileNetV2 · v2
ResNet50
ResNet · 50
SSD MobileNetv1
SSD MobileNet · v1
SSD MobileNetv2
SSD MobileNet · v2
YOLO11l
YOLO11 · l
YOLO11m
YOLO11 · m
YOLO11n
YOLO11 · n
YOLO11s
YOLO11 · s
YOLOv10n
YOLOv10 · n
YOLOv10s
YOLOv10 · s
YOLOv5m
YOLOv5 · m
YOLOv5s
YOLOv5 · s
YOLOv5l
YOLOv5 · l
YOLOv5m
YOLOv5 · m
YOLOv5n
YOLOv5 · n
YOLOv5s
YOLOv5 · s
YOLOv8l
YOLOv8 · l
YOLOv8m
YOLOv8 · m
YOLOv8n
YOLOv8 · n
YOLOv8s
YOLOv8 · s
YOLOv8x
YOLOv8 · x
YOLOv8m
YOLOv8 · m
YOLOv8s
YOLOv8 · s
YOLOv8m
YOLOv8 · m
YOLOv8n
YOLOv8 · n
YOLOv8s
YOLOv8 · s

Query this hardware live.

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

OPEN BENCHMARK EXPLORER →