Developed by Google, Medgemma 4B It is a multimodal chat model exceling at medical text and image comprehension, suitable for accelerating the development of healthcare-based AI applications. Its notable technical trait is the utilization of a SigLIP image encoder pre-trained on de-identified medical data, including various types of medical images.
Input
Output
Context
128K
Max Output
-
Parameters
4.3B
Input Modalities
Output Modalities
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Automatically route workloads to the right model for every task, every time.