Consider Time series analysis: the study of sequential data points collected over time which play a crucial role in fields like finance, healthcare, and weather forecasting. Accurate time series analysis enables the understanding of historical trends and the prediction of future events. With the rise of Large Language Models (LLMs), natural language tasks have become more accessible through intuitive Q&A-style interfaces. Given the structural similarities between time series and language data such as temporal dependencies and sequential patterns, LLMs have slowly become adapted for time series analysis. This project explores the intersection of LLMs and time series forecasting. In Fall 2024, CSE SDP Team 01 conducted a comparative study of three emerging time series LLMs: Chronos, One Fits All, and S2IP-LLM, analyzing both their strengths and limitations. In Spring 2025, the team built an interactive interface that allows users to upload their own datasets and perform forecasting using multiple models simultaneously, enabling direct comparisons and emphasizing ease of use for all types of users, not just ones who are technically adept.