Description

The Coral 4GB System-on-Module (SoM) is a 40mm x 48mm pluggable module that is a fully-integrated system for accelerated ML applications. The SoM helps you build embedded devices that demand fast machine learning (ML) inferencing (includes CPU, GPU, Edge TPU, Wi-Fi, Bluetooth, and Secure Element).

Details

The Coral System-on-Module (SoM) contains NXP’s iMX 8M system-on-chip (SoC), eMMC memory, LPDDR4 RAM, Wi-Fi, and Bluetooth. Still, its unique power comes from Google’s Edge TPU coprocessor for high-speed machine learning inferencing.

Key benefits of the Coral 4 GB SoM

• High-speed and low-power ML inferencing (4 TOPS @2 W)
• A complete Linux system (running Mendel, a Debian derivative)
• Small footprint (40 x 48 mm)
• The Coral 4GB SoM is also included in the Coral Dev Board, a single-board computer that enables fast prototyping and evaluation of the standalone SoM.

Provides a complete system

The Coral 8 GB SoM is a fully-integrated Linux system that includes NXP’s iMX8M system-on-chip (SoC), eMMC memory, LPDDR4 RAM, Bluetooth, Wi-Fi, and the Edge TPU coprocessor for ML acceleration. The module runs a derivative of Debian Linux we call Mendel.

Performs high-speed ML inferencing

The on-board Edge TPU coprocessor is capable of performing 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt). For example, it can execute state-of-the-art mobile vision models such as MobileNet v2 at almost 400 FPS in a power-efficient manner.

Integrates with your custom hardware

The SoM connects to your baseboard hardware with three 100-pin connectors.

Supports TensorFlow Lite

There is no need to build models from the ground up. You can compile TensorFlow Lite models to run on the Edge TPU.

Also available with a baseboard as part of the Coral Dev Board.

Technical Specifications

Specifications