Home › Benchmarks › Hailo-8
Benchmark Explorer · Hailo-8

Hailo-8: 46 benchmark rows, 22% measured.

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

10 of 46 rows are measured and published (class C); the rest are EdgeAIStack-derived (class D). 16 model families. Precisions: INT8 (46). Runtimes: hailo sdk (46). Tasks: detection (25), classification (4), pose (6), segmentation (11).

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
CenterNet405 fps D
DETR30.5 fps D
EfficientDet95 fps C
MobileNet3305 fps D
SSD MobileNet800 fps D
MobileNetV22597 fps D
ResNet1372 fps D
SSD MobileNet1015 fps D
YOLO11185 fps D
YOLO11167 fps D
YOLO11130 fps D
YOLOv5543 fps D
YOLOv5464 fps D
YOLOv8107 fps C
YOLOv8943 fps D
YOLOv8528 fps D

Every model on Hailo-8

CenterNet Resnet18
CenterNet · resnet18
CenterNet Resnet50
CenterNet · resnet50
DETR Resnet18
DETR · resnet18
EfficientDetd0
EfficientDet · d0
MobileNetv1
MobileNet · v1
MobileNetv2
MobileNet · v2
SSD MobileNetv1
SSD 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
YOLO11x
YOLO11 · x
YOLO11m
YOLO11 · m
YOLO11n
YOLO11 · n
YOLO11s
YOLO11 · s
YOLO11m
YOLO11 · m
YOLO11n
YOLO11 · n
YOLO11s
YOLO11 · s
YOLOv5m
YOLOv5 · m
YOLOv5s
YOLOv5 · s
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
YOLOv8n
YOLOv8 · n
YOLOv8s
YOLOv8 · s
YOLOv8l
YOLOv8 · l
YOLOv8m
YOLOv8 · m
YOLOv8n
YOLOv8 · n
YOLOv8s
YOLOv8 · s
YOLOv8x
YOLOv8 · x

Query this hardware live.

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

OPEN BENCHMARK EXPLORER →