# Hailo-8 M.2 AI Accelerator Module (26 TOPS)

**Type:** Product page · **SKU:** WS-27812 · **Brand:** [Waveshare](https://core-electronics.com.au/brands/waveshare-in-australia)
**Page:** https://core-electronics.com.au/hailo-8-m2-ai-accelerator-module-26-tops.html ([markdown](https://core-electronics.com.au/hailo-8-m2-ai-accelerator-module-26-tops.html.md))

Hailo-8 M.2 AI Accelerator Module, based on the 26TOPS Hailo-8 AI processor, Supports Linux/Windows Systems, Optional for PCIe To M.2 Adapter Board,...

## Pricing

- **Price:** $344.95 (inc GST) — $313.59 AUD, exc GST
- **Quantity discounts:** 3+ $304.18 (exc GST) · 5+ $297.91 (exc GST)

## Availability & dispatch

- Available with a lead time — expect dispatch between Sep 09 and Sep 16.

## Description

Hailo-8 M.2 AI Accelerator Module, based on the 26TOPS Hailo-8 AI processor, Supports Linux/Windows Systems

*Note: Does not include PCIe adapter, [we stock several options](https://core-electronics.com.au/catalogsearch/result/?q=pi+5+pcie+m.2)*

### Features

- Hailo-8 AI M.2 module 
    - Powered by 26 Tera-Operations Per Second (TOPS) Hailo-8 AI Processor
    - 2.5W typical power consumption
    - Scalable,enabling simultaneous processingof multi-streams & multi-models
    - Enabling real-time, low latency and high-efficiency AI inferencing on the edge devices
    - Supports TensorFlow, TensorFlow Lite, ONNX, Keras, Pytorch frameworks
    - Supports Linux and Windows
    - Supports the temperature range of -40°C to 85°C
    - 2240 size
 
### Hailo-8 AI M.2 Module Parameters

 | AI performance | 26 TOPS |
|---|---|
| Form Factor | M.2 Key M |
| Power supply | 3.3V ± 5% |
| Power consumption | 2.5W (Typ.) 8.65W (Max.) |
| Interface | PCIe Gen3, 4-lane |
| Certificate | CE, FCC Class A |
| Storage temperature | -40 ~ 85°C |
| Operating temperature | -40 ~ 85°C |
| Operating humidity | 5% ~ 90%RH (no frosting) |
| Dimensions | 22×80mm with breakable extensions to22×42mmand 22×60mm |

Equipped with Hailo-8 AI Accelerator to Step Up Your Edge Product Performance

### Performance parameters

 | NN Model | Input Resolution | mAP | Hailo-8L FPS(batch8) |
|---|---|---|---|
| yolov4\_tiny | yolov4\_tiny | 18.98 | 610 |
| yolov6n | yolov6n | 34.3 | 345 |
| yolov7 | yolov7 | 49.8 | 45 |
| yolox\_s\_wide | yolox\_s\_wide | 42.4 | 75 |
| yolov3 | yolov3 | 38 | 26 |
| yolov8n | yolov8n | 37.23 | 270 |
| yolov8s | yolov8s | 44.75 | 128 |
| yolov8m | yolov8m | 50.08 | 55 |

 | Type | NN Model | Input Resolution | FPS | Power(W) | FPS/W |
|---|---|---|---|---|---|
| Classification | ResNet-50 v1 | 224x224 | 1332 | 3.45 | 386 |
| MobileNet\_v2\_1.0 | 224x224 | 2444 | 2.152 | 1135 |
| EfficientNet\_M | 240x240 | 889 | 3.5 | 254 |
| Object Detection | SSD\_MobileNet\_v1 | 300x300 | 1055 | 2.2 |

### Resources

[Wiki for Hailo-8 M.2 AI Accelerator Module (26 TOPS)](https://www.waveshare.com/wiki/Hailo-8)

## Images

- [Product image 1](https://core-electronics.com.au/media/catalog/product/h/a/hailo-8-3_3.jpg)