Hailo-8™ Benchmarks

The Hailo-8™ AI accelerator brings industry-leading neural processing throughput and power efficiency to support a wide range of AI applications. The table below demonstrates some of Hailo-8’s best-in-class capabilities in the foundational neural tasks of object detection and classification. It achieves very high FPS and power efficiency (FPS/W) across a number of industry-standard neural network models, while also offloading post-processing from the host processor it is working with.

NN ModelInput ResolutionFPSPower [W]FPS/ W
Classification
ResNet-50 v1224×2241,3323.45386
MobileNet_v2_1.0224×2242,4442.1521,135
Object Detection
SSD_MobileNet_v1300×3001,0552.2479
YOLOv5m640×6402184.647.3
Segmentation
stdc11024×1920542.918.6
Multi stream object detection (8 streams)
YOLOv3608×608694.914

Notes

  • Measurements were taken at room temperature through PCIe interface on Hailo-8 evaluation board  ​
  • System host: Intel® Core™ i5-9400 CPU @ 2.90GHz; Models compiled with Hailo Dataflow Compiler version 3.23.0 (SW version 2023-04) ​

Click here and here to see how the Hailo AI accelerator compares.

Breathe life into your edge applications with the Hailo AI processors