Discounts on SMARC® & COM HPC® Development Kits
Excellent CPU Platforms
Embedded Computing Expertise
System Integration Services
Premium Support

Module Store - Building Blocks for Developers of Embedded Computing Systems

Coral Mini PCIe Accelerator

Product information "Coral Mini PCIe Accelerator"
ASUS IoT Coral Mini PCIe Accelerator - Edge AI Computer AI Accelerator The Coral Mini PCIe Accelerator is a Half-Mini PCIe card that brings the Edge TPU ML accelerator to existing systems and products. The Edge TPU is a small ASIC designed by Google that accelerates TensorFlow Lite models in a power efficient manner: it's capable of performing 4 trillion operations per second (4 TOPS), using 2 watts of power—that's 2 TOPS per watt. an available Mini PCIe slot.
ASUS IoT Coral Mini PCIe Accelerator - Edge AI Computer AI Accelerator
The Coral Mini PCIe Accelerator is a Half-Mini PCIe card that brings the Edge TPU ML accelerator to existing systems and products. The Edge TPU is a small ASIC designed by Google that accelerates TensorFlow Lite models in a power efficient manner: it's capable of performing 4 trillion operations per second (4 TOPS), using 2 watts of power—that's 2 TOPS per watt. an available Mini PCIe slot.

Beispiel Menü
Overview
Key Features
  • Google Edge TPU ML accelerator- 4 TOPS total peak performance (int8) - 2 TOPS per watt
  • Integrated power management
  • PCIe Gen2 x1 interface
  • Standard Half-Mini PCIe card
  • Operating temp: -20 to +85 °C
Introduction
The Coral Mini PCIe Accelerator is a Half-Mini PCIe card that brings the Edge TPU ML accelerator to existing systems and products. The Edge TPU is a small ASIC designed by Google that accelerates TensorFlow Lite models in a power efficient manner: it's capable of performing 4 trillion operations per second (4 TOPS), using 2 watts of power—that's 2 TOPS per watt. 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 400 FPS, in a power efficient manner. See more performance benchmarks. Works with Debian Linux and Windows Integrates with any Debian-based Linux or Windows 10 system with a compatible card module slot. Supports TensorFlow Lite No need to build models from the ground up. TensorFlow Lite models can be compiled to run on the Edge TPU.   For more product and technical information, please visit Coral Mini PCIe Accelerator website
All data is for information purposes only. The specification is subject to change without notice in advance. Any configuration other than original product specification is not guaranteed. Although all the information contained within this website is carefully checked, no guarantee of correctness is implied or expressed.
Please always double-check the latest version of the product specification of the product manufacturer. Manufacturer Product Website: Coral Mini PCIe Accelerator
Product names, logos, brands, and other trademarks featured or referred are the property of their respective trademark holders. These trademark holders are not affiliated with MCTX Mobile & Embedded Computers GmbH.

OEM System Integration Support

All documents found on this page are subject to change without notification. Always ensure that you work with the latest version.

We would be happy to assist you in selecting the optimal hardware platform for your application.

If you have any questions, whether technical or commercial, about our products or services, don’t hesitate to contact us. We look forward to hearing from you.

You can reach us by phone at +49 (0)7665/9390-185 (Monday to Friday from 8:00 AM to 8:00 PM). Alternatively, you are welcome to contact us anytime via the contact form at the end of this page. If you cannot reach us by phone, please send us a brief message via the contact form – we will get back to you as soon as possible.

Please note that we offer our services exclusively to Original Equipment Manufacturers. We do not sell to private persons or resellers.
Contact Form
Privacy *
Fields marked with asterisks (*) are required.
Vielen Dank für Ihre Anfrage. Wir haben Ihre Anfrage erhalten und werden uns so schnell wie möglich mit Ihnen in Verbindung setzen.

MCTX Mobile & Embedded Computers GmbH was founded in 2010 and focuses on the development and marketing of compact, high-performance, energy-efficient, and scalable computer systems and system components for mobile and stationary professional use in both indoor and outdoor environments.  

We consider ourselves a reliable and experienced partner for companies and organizations that integrate these technologies into their processes or products.  Our goal is to offer our customers SOLUTIONS that fully meet the requirements of their tasks.

Our company headquarters is located in southwestern Germany, in Gottenheim near Freiburg im Breisgau, close to the borders of France and Switzerland.

Service Portfolio

Depending on the project requirements, we offer our customers a wide range of products and outsourcing services: technology consulting for selecting the processor platform, delivery of key components, and the commissioned delivery of fully integrated, custom systems.

Over the years, our team has gained valuable experience in the integration of energy-efficient computing technologies. We provide this engineering know-how to our customers in order to optimize product and development costs as well as time-to-market.


Applications

Our boards and systems are used in a variety of applications in the field, in laboratories, in factory automation, and in OEM products, such as in the validation of semiconductor chips, in Lidar systems for 3D object measurement, in autonomous vehicles, various measurement and diagnostic systems, or in mobile data collection in the agricultural and forestry sectors.

Technologies

Our systems are based on state-of-the-art technologies used in modern servers, notebooks, tablet PCs, and navigation systems. The use of modular and industrial-grade system concepts enables long-lasting and scalable systems.