A brain tumor refers to an abnormal proliferation of cells within the brain or its surrounding tissues, categorized based on the type of cells involved. Identifying and classifying these tumors presents a significant challenge for neurologists, with early diagnosis being crucial for effective treatment planning. This study employs YOLOv8, a sophisticated deep learning model, to categorize brain tumors into four types: Glioma, Meningioma, Pituitary tumor, and No Tumor. The entire work has been performed by utilizing 7023 MRI Scans of the Brain which are obtained from Kaggle. It’s found that enhancement of classification accuracy and other medical metrics is important for early diagnosis and better treatment. Hence, the proposed work used YOLOv8 for better results. The final potency in terms of accuracy is 99.39%. The overall performance metrics are calculated based on the testing results, which are as follows: Precision: 99.37%, Sensitivity: 99.34%, Specificity: 99.79%, F1-Score: 99.35%. It is identified that the proposed work with YOLOv8 has shown improved performance metrics compared to existing state-of-the-art models. By evaluating YOLOv8’s efficacy in brain tumor classification, this study hopes to advance the field of deep learning applications for medical image analysis. This work can be extended further to implement the model on cloud services for effective deployment.