The surging demand for beef in Indonesia poses a significant challenge for the food industry, leading to fraudulent practices among meat traders. To meet the high consumer demand and gain higher profits, fresh beef is mixed with spoiled meat. Unfortunately, many consumers are unable to distinguish between fresh and spoiled beef, relying solely on the meat's aroma to determine its quality. However, recognizing spoiled beef requires considering other indicators of spoilage. To address this issue, researchers focused on developing a beef quality classification system using the Convolutional Neural Network (CNN) method. The study involved implementing TensorflowLite on Android devices and training the CNN model with deep learning algorithms to recognize visual patterns in beef images. The Android application provides clear and user-friendly classification results. The developed beef quality classification system achieved remarkable accuracy, with a precision of 97%, a recall of 96%, and an f1-score of 97%. With 100 beef images as test data, the system demonstrated an accuracy rate of 95.69%. This advancement is expected to improve the efficiency and quality of beef processing in Indonesia, ensuring consumers receive genuine and safe products.