Gemma: Google DeepMind's Open Language Models

These sources collectively introduce and explain MedGemma and MedSigLIP, two collections of open-source AI models developed by Google Health for healthcare applications. The MedGemma collection consists of generative models (4B multimodal and 27B text-only variants) designed for tasks requiring text generation, like report creation or visual question answering, and is based on the Gemma 3 architecture. MedSigLIP is a lightweight image and text encoder primarily for medical image interpretation without text generation, such as classification and retrieval. Both are part of the Health AI Developer Foundations (HAI-DEF) initiative, emphasizing flexibility, privacy, and customization through open access to model weights, allowing developers to fine-tune them for specific clinical use cases. The documents also highlight the evaluation and responsible deployment efforts for these models, aiming to advance AI in healthcare while mitigating potential risks.