About this item

The Coral TPU M.2 B+M Module is a compact machine learning accelerator developed by Google to enhance edge AI capabilities in embedded systems. Equipped with the Edge TPU, a purpose-built ASIC, it delivers up to 4 TOPS (trillion operations per second) while consuming only 2 watts of power, making it highly efficient for real-time inferencing tasks. The module features a PCIe Gen2 x1 interface and is designed in the M.2-2280 B+M key form factor, ensuring compatibility with a wide range of devices, including embedded platforms, mini-PCs, and industrial gateways. With dimensions of 22.0 x 80.0 x 2.35 mm and a weight of 6 grams, it is suitable for space-constrained applications. The module operates within a temperature range of -20°C to +85°C and supports a 3.3V ±10% DC supply. It is ideal for deploying TensorFlow Lite models, such as MobileNet v2, achieving nearly 400 frames per second, thereby reducing latency and dependency on cloud services. The Coral TPU M.2 B+M Module is an excellent choice for developers seeking to integrate efficient AI processing into their edge devices