Hailo-8™ M.2 AI Acceleration Module
Step Up Your Edge Product Performance with Best-In-Class AI Processor Packaged in A Module
The Hailo-8™ M.2 Module is an AI accelerator module for AI applications, compatible with NGFF M.2 form factor M, B+M and A+E keys. The AI module is based on the 26 tera-operations per second (TOPS) Hailo-8™ AI processor with high power efficiency. The M.2 AI accelerator features a full PCIe Gen-3.0 2-lane interface (4-lane in M-key module), delivering unprecedented AI performance for edge devices. The M.2 module can be plugged into an existing edge device with M.2 socket to execute in real-time and with low power deep neural network inferencing for a broad range of market segments. Leveraging Hailo’s comprehensive Dataflow Compiler and its support for standard AI frameworks, customers can easily port their Neural Network models to the Hailo-8 and introduce high-performance AI products to the market quickly.
Learn about our partner ecosystem here
|Form Factor||M.2 Key M||M.2 Key B+M||M.2 Key A+E|
|AI Processor||Hailo-8™ AI processor with up to 26 TOPS and best-in-class power efficiency|
|Dimensions||22 x 42 mm
With breakable extensions to 22 x 60 and 22 x 80 mm
|22 x 30 mm|
|Interface||PCIe Gen-3.0, 4 lanes (up to 32 Gbs)||PCIe Gen-3.0, 2 lanes (up to 16 Gbs)|
|Supported Frameworks||TensorFLow, TensorFlow Lite, ONNX, Keras, Pytorch|
|Supported OS||Linux, Windows|
- Hailo-8 figures are based on SDK version 3.12.0 (November 2021), measured at room temperature on a single Hailo-8 device through PCIe interface on a Hailo evaluation board (system host: Intel® Core™ i5-9400 CPU @ 2.90GHz)
- Intel Myriad X figures sourced from: https://docs.openvinotoolkit.org/latest/openvino_docs_performance_benchmarks_openvino.html , retrieved 12/07/21 for version 2021.4
- Google Edge TPU figures sourced from: https://coral.ai/docs/module/datasheet/ (with power figures) ; https://coral.ai/docs/edgetpu/benchmarks/ (throughput only), retrieved 12/07/21 ; and https://coral.ai/models/image-classification/, retrieved 08/08/21
- FPS is converted from latency in ms (1 divided by ms/1000)
- Hailo-8 and Edge TPU figures are for batch=1 and INT8, while Myriad X is batch=1 and FP16
Documents marked with a lock icon are available for registered users only. To sign up click here
Breathe life into your edge products
with the Hailo-8™ AI processor
Hailo-8TM Starter Kit is available now!
Please fill out the form, and one of our representatives will get back to you shortly.