The characteristic of leukemia, a type of blood cancer, is the unrestrained production of abnormal white blood cells, which replace normal cells and compromise the body’s ability to fight infections. Leukemia management and patient outcomes both benefit from early diagnosis and therapy. Machine learning (ML) and deep learning (DL) techniques have gained popularity in the field of medical diagnostics in recent years due to their promise to improve efficiency and accuracy. This research focuses on applying deep learning techniques to automate the classification of leukemia cells based on microscopic images of white blood cells, supporting ongoing attempts to enhance healthcare diagnostics. Leukemia is identified using EfficientNetB1 from images of blood smears. A 97.50% accuracy was obtained with EfficientNetB1. Owing to the results’ accuracy, the proposed model may be helpful for identifying leukemia in real-world scenarios and promoting early leukemia detection.