Short-term precipitation forecasting, or nowcasting, plays a vital role in mitigating the impacts of extreme weather by supporting timely decisions in urban planning, flood management, and transportation systems. In this thesis, we cast precipitation nowcasting as a video prediction problem, where the goal is to generate future radar images given a sequence of past observations. To address this, we propose BlockGPT, a generative transformer model that predicts entire frames autoregressively, capturing spatial dependencies within each frame using bidirectional attention, while maintaining temporal causality across frames. BlockGPT is evaluated on two real-world radar datasets: KNMI (Netherlands) and SEVIR (United States), across two forecasting tasks involving different temporal resolutions. The model is benchmarked against existing state-of-the-art approaches-NowcastingGPT and Diffcast-which represent token-based and diffusion-based paradigms, respectively. Our results show that BlockGPT offers competitive performance and strong capabilities in detecting and localizing significant rainfall events, while also enabling faster inference. These properties make it a promising candidate for real-time, threshold-aware weather forecasting systems.