unsloth/medgemma-1.5-4b-it

MedGemma 1.5 4B is a multimodal instruction-tuned variant of Google's Gemma 3 architecture, specifically trained for performance on medical text and image comprehension. Developed by Google, this 4 billion parameter model excels at interpreting high-dimensional medical imaging, whole-slide histopathology, longitudinal medical imaging, anatomical localization, and understanding electronic health records. It provides strong baseline medical image and text comprehension, making it efficient for developers to adapt for healthcare-based AI applications.