The Virtual Boxing Trainer project aims to revolutionize boxing training by integrating wearable technology with intelligent data analysis. Using Arduino Nano BLE 33 boards equipped with inertial measurement units (IMUs), this system records, classifies, and analyzes boxing moves, delivering an interactive and engaging training experience for users. Designed for fitness enthusiasts, professional boxers, coaches, and gyms, the trainer provides a real-time prediction of punch types, enabling users to instantly identify and assess their movements. It also gives real-time feedback on performance metrics such as the number of punches thrown in each punch category (Punch, Hook, Upper, and Block) and the punch power. Additionally, it classifies users into skill levels (beginner, intermediate, or advanced) based on the total punches they have thrown. The trainer evaluates punch power of users, categorizing it as low, moderate, or high, by capturing and analyzing the real-time punch power of each punch. A user interface (UI) has been developed to enhance the usability and accessibility of the system. The UI allows users to view their real- time prediction punch types, training performance metrics including the punch count of each punch category, and power categorization, in an intuitive and visually engaging manner.