MedGemma A Gemma 3 variant optimized for medical text and image comprehension Download from Hugging Face Access on Vertex AI MedGemma can be fine-tuned to improve performance for medical text and imageapplications and used as a privacy-preserving tool within agentic systems. Read docs View model card Potential use cases Medical image classificationAdaptable for use in classifying medical images including radiology, digital pathology, fundus and skin images. Medical image interpretationAdaptable for use in generating medical image reports or answering natural language questions about medical images. Text-based medical question answeringAdaptable for use cases that require medical knowledge, including patient preclinical interviews, triaging, clinical decision support, and summarization. Model categories 4BA multimodal model adaptable for medical image classification and interpretation 27BA text-only model optimized for inference-time computation Developers should validate model performance and make necessary improvements before deploying it in a production environment.
