The future of enterprise AI hinges on customized language models optimized for specific domains. Small Language Models (SLMs) are more computationally efficient, requiring less memory and storage, and are often more effective during inference. Training and deploying SLMs is cost-effective, making them accessible to a broader range of businesses and ideal for edge computing applications. SLMs are more adaptable to specialized applications and can be fine-tuned for specific tasks more efficiently than larger models. In this session, we will explore the potential of fine-tuning SLMs, such as Gemma, to develop an AI-powered medical chatbot that can assist patients and healthcare providers by answering general medical questions about diseases, health conditions, and treatment options, as well as summarizing complex medical documents or articles with ease.