The Coral USB Accelerator adds an Edge TPU coprocessor to  your system. It includes a USB-C socket you can connect to a  host computer to perform accelerated ML inferencing.  The on-board 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. For example, one Edge TPU can execute state-of-the-art mobile vision models such as MobileNet v2 at almost 400  frames per second. This on-device ML processing reduces latency, increases data privacy, and removes the need for a  constant internet connection.