Explore the evolving landscape of machine learning on edge devices in this informative conference talk. Discover how hardware providers are pushing the boundaries of small footprint, low-powered edge devices capable of running hardware-accelerated machine learning without relying on cloud backends. Learn about the range of ML-capable edge devices, from microprocessor-based real-time systems to fully-fledged embedded Linux devices. Delve into the challenges of large-scale deployment, including model adaptation and size reduction. Gain insights into over-the-air updates for microprocessors and Dockerized deployment for embedded Linux devices. Witness a practical demonstration of a basic computer vision application deployed on three small-scale embedded Linux devices: Raspberry Pi, Google Coral, and NVIDIA Jetson.