This is google/medgemma-27b-text-it with the vision tower and embeddings of google/gemma-3-27b-it attached to restore multimodality.
I do not expect the vision function to work with the med data to the same degree as the multimodal 4B medgemma. It has not been trained beyond the instruct model.
- Downloads last month
- 5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support