ASUS AI accelerator card is a full height, half length, PCIe Gen3 AI acceleration card based on Google Coral Edge TPU processor. It allows users to build intelligent AI inference devices base on existing devices with PCIe Gen3 slot.For more information and support, please visit Google Coral website

Performs high-speed ML inferencing

Each Edge TPU coprocessor is capable of performing 4 trillion operations per second (4 TOPS), using 2 watts of power. For example, it can execute state-of-the-art mobile vision models such as MobileNet v2 at almost 400 FPS, in a power efficient manner.

With the 8 to 16 Edge TPUs in this PCIe card, you can multiply the inferences per second (32 TOPS to 64 TOPS) in several ways, such as by running several models in parallel or pipelining one model across all Edge TPUs.

See more Edge TPU performance benchmarks.

Supports TensorFlow Lite

No need to build models from the ground up. TensorFlow Lite models can be compiled to run on the Edge TPU.

Supports AutoML Vision Edge

Easily build and deploy fast, high-accuracy custom image classification models to your device withAutoML Vision Edge.