---
title: medgemma-1.5-4b-it
description: MedGemma 1.5 is Google's 4B multimodal medical model, built on Gemma 3. It reads 2D medical images, 3D CT and MRI volumes, whole-slide pathology images, longitudinal chest X-rays and medical documents, and answers in text. Access requires accepting Google's Health AI Developer Foundations terms on Hugging Face.
tags:
- clinical
- clinical-reasoning
- dermatology
- gemma3
- image-text-to-text
- imaging
- medical
- multimodal
- radiology
license: other
source_url: https://huggingface.co/google/medgemma-1.5-4b-it
---

# medgemma-1.5-4b-it

> **Mirrored metadata.** This card is reproduced on Atlas for discovery. The artifact itself is not hosted here — follow the source link for the files, and refer to the upstream licence for terms of use.

MedGemma 1.5 is Google's 4B multimodal medical model, built on Gemma 3. It reads 2D medical images, 3D CT and MRI volumes, whole-slide pathology images, longitudinal chest X-rays and medical documents, and answers in text. Access requires accepting Google's Health AI Developer Foundations terms on Hugging Face.

Upstream identifier: `google/medgemma-1.5-4b-it`. Paper: [arXiv:2604.05081](https://arxiv.org/abs/2604.05081).

**Source:** https://huggingface.co/google/medgemma-1.5-4b-it

**Licence:** other

_This model is part of the Atlas demo catalogue. See the repository history for provenance._