Features & Benefits
- On-board Edge TPU coprocessor performs high-speed ML inferencing
- Capable of performing 4 trillion operations (tera-operations) per second (TOPS)
- Uses 0.5 watts for each TOPS (2 TOPS per watt)
- Can execute state-of-the-art mobile vision models such as MobileNet v2 at 400 FPS
- Supports TensorFlow Lite without building models from the ground up
- Works with Debian Linux and integrates with any Debian-based Linux system with a compatible card module slot



