Home › Benchmarks › Hailo-8L
Benchmark Explorer · Hailo-8L
Hailo-8L: 39 benchmark rows, 18% measured.
Method v1.0 · dataset 2026-09-07 · verified 2026-09-07 · last updated September 2026
7 of 39 rows are measured and published (class C); the rest are EdgeAIStack-derived (class D). 13 model families. Precisions: INT8 (39). Runtimes: hailo sdk (39). Tasks: detection (20), classification (4), pose (6), segmentation (9).
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.
| Family | INT8 |
|---|---|
| DETR | 23.4 fps D |
| MobileNet | 2565 fps D |
| MobileNetV2 | 1738 fps D |
| ResNet | 172 fps C |
| SSD MobileNet | 356 fps D |
| YOLO11 | 157 fps D |
| YOLO11 | 151 fps D |
| YOLO11 | 129 fps D |
| YOLOv5 | 124 fps D |
| YOLOv5 | 145 fps D |
| YOLOv8 | 65 fps C |
| YOLOv8 | 195 fps D |
| YOLOv8 | 168 fps D |
Every model on Hailo-8L
DETR Resnet18
DETR · resnet18
MobileNet Ssd Mobilenet V1
MobileNet · ssd-mobilenet-v1
MobileNetv1
MobileNet · v1
MobileNetv2
MobileNet · v2
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
YOLOv8m
YOLOv8 · m
YOLOv8n
YOLOv8 · n
YOLOv8s
YOLOv8 · s
Links
- Live engine: https://edgeaistack.ai/engines/benchmark-explorer/?hw=hailo_8l&model=detr&variant=resnet18&mv=1.0&dv=2026-09-07
- Methodology: /methodology/benchmark-explorer/
- Dataset: /datasets/benchmarks-v2.json
- All hardware: /benchmarks/
Query this hardware live.
Filter by model, precision or runtime and get the matching rows with a permanent link.