We track commercial real estate investors and rank potential transactions. Large Language Models (LLMs) in the general domain, such as ChatGPT, have shown remarkable success in producing human-like responses. However, such models have not been tailored to the commercial real estate domain, resulting in inability to give plausible recommendations for buy/sell matching and investors profiling. LombardGPT analyzes billions of datapoints and is able to accurately match sell side requests with potential buyers in all asset classes across global markets.