About this item

The Coral M.2 Accelerator with Dual Edge TPU is a high-performance module designed to integrate advanced machine learning capabilities into systems with an M.2 E-key slot. This accelerator features two Google Edge TPU coprocessors, each capable of performing 4 trillion operations per second (4 TOPS) with a power efficiency of 2 TOPS per watt. Together, they deliver a total peak performance of 8 TOPS, enabling rapid execution of TensorFlow Lite models, such as MobileNet v2, at nearly 400 frames per second. This on-device processing reduces latency, enhances data privacy, and eliminates the need for constant internet connectivity. The module connects via a PCIe Gen2 x1 interface and operates within a temperature range of -40 to +85°C, making it suitable for embedded platforms, mini-PCs, and industrial gateways. It supports both Debian-based Linux and Windows 10 systems, offering flexibility for various applications. The Coral M.2 Accelerator with Dual Edge TPU is ideal for developers and engineers seeking to add powerful AI capabilities to their devices, facilitating real-time inferencing for applications like image and video classification, object detection, and voice recognition.