Join us as we delve into the fascinating world of deploying Artificial Intelligence (AI) and Machine Learning (ML) models in diverse edge deployment scenarios. This talk is designed for technology enthusiasts, developers, and industry professionals seeking insights into running AI/ML models efficiently at the edge. We will compare the components used in traditional cloud-based Kubernetes distributions with lightweight Kubernetes distributions optimized for edge devices such as MicroShift. We'll explore crucial factors like power consumption, model size, and performance, shedding light on the considerations necessary for successful edge deployments. Additionally, we'll present a practical example of serving multiple models and discuss strategies to minimize inference process switching time in time-sensitive situations. Learn how open source components can empower you to navigate the challenges of running AI and ML models at the edge efficiently.