Techbase Reveals Raspberry Pi Powered AI Gateway

ModBerry AI GATEWAY 9500-CM4
(Image credit: Techbase)

A recent update to Techbase's range of Modberry industrial controllers sees the new Modberry AI Gateway 9500-CM4 join their range of Modberry 500 CM4 DIN Rail computers. As you have guessed from the name, these units feature the new Raspberry Pi Compute Module 4, but the AI Gateway 9500-CM4 also comes with a Google Coral Tensor Processing Unit (TPU) for faster machine learning processing.

At the core of the industrial-focused product is the Raspberry Pi 4's BCM2711 System on Chip, featuring a 64-bit quad-core Arm processor running at 1.5 GHz. There are 32 variants of the Raspberry Pi Compute Module 4, each with different RAM, eMMC storage, and WiFi options. Also at the core is Google's Coral Edge TPU, connected to the Compute Module 4's exposed PCIe interface. 

The Coral Edge TPU provides four trillion operations per second and increases the processing power required for AI / Machine Learning projects using TensorFlow Lite. Enabling ModBerry AI GATEWAY 9500-CM4 to be used in industrial projects where machine learning and AI would benefit, such as automotive and Internet of Things projects.

ModBerry AI GATEWAY 9500-CM4

(Image credit: Techbase)

"ModBerry AI GATEWAY 9500-CM4 can be equipped with serial RS-232/485 ports, range of digital and analog I/Os, USB, HDMI and Ethernet. Interfaces can be expanded with additional I/Os and opto-isolation, relays, Ethernet, 1-Wire, CAN, M-Bus Master and Slave, accelerometer, OLED screen and many more features like TPM Security Chip, eSIM and SuperCap backup power support. " - Techbase Press Release.

At this time Techbase is working on the prototypes, and delivery times are around two months, depending on the supply of Compute Module 4 units. The price will also vary based upon your chosen configuration.    

Les Pounder

Les Pounder is an associate editor at Tom's Hardware. He is a creative technologist and for seven years has created projects to educate and inspire minds both young and old. He has worked with the Raspberry Pi Foundation to write and deliver their teacher training program "Picademy".