Compact List
Ara-1 M.2 (M-Key) Module for AI-Integrated Cameras and Embedded Systems
This page contains information on a product not recommended for new designs. Specifications and information herein are subject to change without notice. For additional information, please contact NXP support or your NXP sales representative.
The Ara-1 M.2 module is a compact AI accelerator designed for edge computing, offering real-time AI inferencing with low power consumption and fast processing speeds. It integrates the Ara-1 Discrete Neural Processing Unit, 1 GB LPDDR4 memory, and supports AI frameworks like TensorFlow, PyTorch and ONNX. It enables on-device AI without cloud connectivity, ensuring low latency and enhanced privacy.
Product Details
Block Diagram
Choose a diagram:
Supported Devices
Processors and Microcontrollers
Discrete Neural Processing Units
- ARA-1-DNPU: Ara-1: Discrete NPU for Optimized Edge-AI
i.MX 8 Applications Processors
- i.MX8MPLUS: i.MX 8M Plus – Arm® Cortex®-A53, Machine Learning, Vision, Multimedia and Industrial IoT
i.MX 9 Processors
- i.MX95: i.MX 95 Applications Processor Family: High-Performance, Safety Enabled Platform with eIQ® Neutron NPU
Features
AI model frameworks supported
- TensorFlow
- PyTorch
- ONNX
Form factor
- M.2-2280 (M-Key) compliant; (22 mm x 80 mm x 10 mm)
AI Model Architectures Supported
- Convolutional Neural Networks (CNNs)
Performance1
- Up to 6 eTOPS*
Interface
- PCIe Gen3 x4
Memory
- 1 GB LPDDR4 (stores all user models)
Operating system support (Runtime)
- Linux
Operating voltage (DC supply)
- 5 V ±10 %
