Software
Quick reference to our software types.
1 software file
-
AI/ML Modeling Tools
Ara Software Development Kit
Note: For better experience, software downloads are recommended on desktop.
Compact List
Ara-1 USB 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 USB module is a compact, plug-and-play AI accelerator featuring the Ara-1 discrete neural processing unit (DNPU) designed for edge AI applications. It supports multiple AI frameworks, including TensorFlow, PyTorch and ONNX. Ara-1 USB module is capable of running models with low latency. The module offers seamless integration with Linux-based host systems, enabling rapid deployment of AI solutions.
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
- TensorFlow
- PyTorch
- ONNX
Board size (W x L x H)
- 27 mm x 50 mm x 5 mm (board only)
- 48.3 mm x 91.5 mm x 23.8 mm (with heat sink)
AI Model Architectures Supported
- Convolutional Neural Networks (CNNs)
Performance1
- Up to 6 eTOPS*
Interface
- USB-Type C port (3.2 Gen 1)
- 2nd Type-C port (additional power, if needed)
Memory
- 1 GB LPDDR4 (stores all user models)
Operating system support (Runtime)
- Linux
Operating voltage (DC supply)
- 5 V ±10 %
Chip package
- 15 mm x 15 mm EHS-FCBGA