Hailo-8 AI
Accelerator

Hailo-8 Overview

The World’s Best Performing AI Processor for Edge Devices

The Hailo-8 edge AI processor, featuring up to 26 tera-operations per second (TOPS), significantly outperforms all other edge processors. Its area and power efficiency are far superior to other leading solutions by a considerable order of magnitude – at a size smaller than a penny even including the required memory. With an architecture that takes advantage of the core properties of neural networks, our neural chip allows edge devices to run deep learning applications at full scale more efficiently, effectively, and sustainably than other AI chips and solutions, while significantly lowering costs. Learn about our partner ecosystem here.

Breathe life into your edge applications with the Hailo AI processors

Features

Key Features & Benefits

Unprecedented AI compute power of 26 Tera-Operations Per Second (TOPS)

Best-in-class power efficiency with typical power consumption of 2.5W

Enabling real-time, low latency & high-efficiency AI inferencing on edge devices

Highest cost-efficiency (TOPS/$) compared with existing solutions

Scalable:
– Enabling simultaneous processing of multi-streams & multi-models
– Supporting multiple Hailo-8 devices

Commercial, Industrial & Automotive grades, supporting:
– Industrial: -40°C to 85°C
– Automotive: -40°C to 105°C

Easy hardware integration; Does not require external memory

Holistic solution comprised of hardware and software

Proprietary novel structure-driven Dataflow architecture

Neural Network Models & Application Support

AI frameworks: TensorFlow, TensorFlow Lite, Keras, PyTorch & ONNX

Host Architectures: X86, ARM

OSs: Linux, Windows

Comprehensive dataflow compiler enables customer to port their neural network models easily & quickly

Automotive Compliance

A-SPICE L2 development flow

AEC-Q100 Grade 2 compliant

ISO-26262 ASI-B (D) compliant 

Explore More

Product Brief
Hailo-8 AI Processor Product Brief
Blog
AI Object Detection on the Edge: Making the Right Choice
When choosing an AI object detection network for edge devices, there are many factors you should consider: compute power, memory resources, and many more. Which ones? This blogpost outlines everything you need to know when choosing an object detection network for your edge application. But remember, the Hailo-8 processor provides high-performance computing on the edge and can…

Performance

 

 

Benchmarks

NN Model Input Resolution FPS Power (W) FPS/W

Classification

ResNet-50 v1

224×224

1,312

3.4

391

MobileNet_v2_1.0

224×224

2,444

2.1

1,163

EfficientNet_M

240×240

897

3.5

254.2

ViT_base

224×224

126

2.5

52.5

Object Detection

SSD_MobileNet_v1

300×300

1,016

2.2

461.8

YOLOv5m

640×640

218

4.7

46.3

Semantic Segmentation

stdc1

1,024×1,920

59

3.1

19

Notes:

  1. Batch 8
  2. Measurements were taken at room temperature through PCIe interface on Hailo-8 evaluation board  
  3. System host: Intel® Core™ i5-9400 CPU @ 2.90GHz; Models compiled with Hailo Dataflow Compiler version 3.26.0 (SW version 2024-01)

Order Starter Kit

Get started with
Hailo-8

The Hailo-8 starter kit includes:

  • Hailo-8 M.2 Module (key M, key A+E or key B+M)
  • Thermal management kit includes the metal cubes, thermal pads, and thermal adhesive tape
  • Screw and screwdriver

Hailo-8 Starter Kit is available now!

Hailo-8 Starter Kit Module Part Number Price

M.2 Key M 2280 ET

HM218B1C2XAE

$179

M.2 Key B+M 2280 ET

HM218B1C2ZAE

$179

M.2 Key A+E 2230 ET

HM218B1C2YAE

$179

Explore More

Product Brief
Hailo-8 M.2 Starter Kit Product Brief

EU Research and Innovation Program

This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No. 849921

Breathe life into your edge applications with the Hailo AI processors