MedGemma  |  Health AI Developer Foundations  |  Google for Developers
Skip to main content
Health AI Developer Foundations
Home
Docs
Developer Forum
Blog
Showcase
Shortcuts
/
English
Deutsch
Español
Français
Indonesia
Português – Brasil
Русский
中文 – 简体
日本語
한국어
Sign in
Docs
Health AI Developer Foundations
Home
Docs
Developer Forum
Blog
Showcase
Shortcuts
Health AI Developer Foundations
Overview
Community guidelines
Frequently asked questions
Implementation partners
Engage with us
MedGemma
Overview
Get started
Model card - 1.5
Model card - 1
MedASR
Overview
Get started
Model card
MedSigLIP
Overview
Get started
Model card
TxGemma
Overview
Get started
Model card
HeAR
Overview
Get started
Model card
Serving API
Path Foundation
Overview
Get started
Model card
Serving API
Derm Foundation
Overview
Get started
Model card
Serving API
CXR Foundation
Overview
Get started
Model card
Serving API
Libraries
Overview
LangExtract
Model data
DICOMweb storage
Legal
Terms of use
Prohibited use policy
Can I help?
Home
Products
Health AI Developer Foundations
Docs
MedGemma
Stay organized with collections
Save and categorize content based on your preferences.
Page Summary
outlined_flag
MedGemma is Google's collection of open models for medical text and image comprehension, built on Gemma 3, designed to accelerate building healthcare-based AI applications.
MedGemma is available in a 4B multimodal version, a 27B text-only version, and a 27B multimodal version.
Common use cases for MedGemma include medical image interpretation, medical text comprehension, and clinical reasoning.
MedGemma requires validation for specific use cases and can be further adapted through prompt engineering, fine-tuning, or agentic orchestration to improve performance.
The MedGemma collection contains Google's most capable open models for medical
text and image comprehension, built on Gemma 3. Developers can use MedGemma to
accelerate building healthcare-based AI applications. The following versions of
MedGemma are available:
MedGemma 1.5: 4B multimodal
MedGemma 1: 4B multimodal version and 27B text-only and multimodal versions.
For details about how to use the model and how it was trained, see the MedGemma
model card.
Common use cases
The following sections present some common use cases for the model. You're free
to pursue any use case, as long as it adheres to the Health AI Developer
Foundations terms of
use.
Medical image interpretation
MedGemma's pre-trained multimodal variants are well-suited for tasks like
generating medical image reports or answering natural language questions about
medical images. While its baseline performance is strong compared to similar
models, MedGemma isn't yet clinical-grade and will likely require further
fine-tuning.
MedGemma 1.5 4B enables developers to more effectively adapt MedGemma for
applications that involve several medical imaging modalities including
high-dimensional medical imaging CT (Computed Tomography), MRI (Magnetic
Resonance Imaging), Whole-slide histopathology imaging (WSI), longitudinal
medical imaging, and anatomical localization:
Medical text comprehension and clinical reasoning
MedGemma can be adapted for use cases that require medical knowledge. Such use
cases may include patient interviewing, triaging, clinical decision support, and
summarization. For most use cases, the larger MedGemma 27B model will generally
yield the best performance. Both sizes of MedGemma have a strong baseline
performance compared to similar models of their size, but developers should
validate their adapted model's performance and make necessary improvements
before deploying in a production environment.
MedGemma 1.5 4B delivers improved accuracy on medical text reasoning. The
updated model specifically expands support for data processing applications
including medical document understanding via extraction of structured data from
unstructured medical lab reports and Electronic Health Record (EHR)
understanding for the interpretation of text-based EHR data.
Adapting MedGemma
MedGemma is a developer model that requires validation on the developer's
intended use case. Based on those validation results, the user will likely need
to further adapt the model to improve performance. Below are some types of
adaptation developers can use to improve MedGemma's performance for their use
cases.
Prompt engineering/in-context learning
For certain use cases, MedGemma's baseline performance may be sufficient after
careful prompting, potentially including few-shot examples of desirable example
responses within the prompt, in other words in-context learning. Prompt
engineering may also use MedGemma to break the task into subtasks that can be
performed separately. Adaptations using prompt engineering require the same
level of validation as any other type of adaptation.
Fine-tuning
MedGemma can be fine-tuned for improved performance on the existing tasks it's
been trained on, or to add additional tasks to its repertoire. For an example of
how to fine-tune MedGemma using LoRA (a
parameter-efficient fine-tuning technique), see this
notebook.
To see an example of the use of reinforcement learning with MedGemma, see this
notebook.
Users can specifically fine-tune the language model decoder component to help
the model better interpret the visual tokens produced by the image encoder, or
fine-tune both.
Agentic orchestration
MedGemma can be used as a tool within an agentic system, coupled with other
tools, like web search, FHIR
generators/interpreters, Gemini
Live for bidirectional audio
conversation, or Gemini 2.5
Pro for function calling or
reasoning. MedGemma can also be used to parse private health data locally before
sending anonymized requests to centralized models like Gemini 2.5 Pro.
Next steps
Get started using the model
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2026-01-13 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2026-01-13 UTC."],[],[]]
Connect
Blog
Bluesky
Instagram
LinkedIn
X (Twitter)
YouTube
Programs
Google Developer Program
Google Developer Groups
Google Developer Experts
Accelerators
Google Cloud & NVIDIA
Developer consoles
Google API Console
Google Cloud Platform Console
Google Play Console
Firebase Console
Actions on Google Console
Cast SDK Developer Console
Chrome Web Store Dashboard
Google Home Developer Console
Android
Chrome
Firebase
Google Cloud Platform
Google AI
All products
Terms
Privacy
Manage cookies
English
Deutsch
Español
Français
Indonesia
Português – Brasil
Русский
中文 – 简体
日本語
한국어