M.2 Accelerator with Dual Edge TPU

Coral M.2 Accelerator with Dual Edge TPU doubles the inferences per second (8 TOPS). The module is an M.2 module (E-key) that includes two Edge TPU ML accelerators, each with their own PCIe Gen2 x1 interface. For example, this can be accomplished by running two models in parallel or pipelining one model across both Edge TPUs. The small (22.0mm x 30.0mm x 2.8mm) module accelerates TensorFlow Lite modules in a power-efficient manner using 2 watts of power (2 TOPS per watt). One Edge TPU can execute state-of-the-art mobile vision models such as MobileNet v2 at almost 400 frames per second. The Coral M.2 Accelerator with Dual Edge TPU on-device machine-learning processing reduces latency, increases data privacy, and removes the need for a constant internet connection.

DataSheet: