MedGemma 1.5 4B
Release in the MedGemma family · version 1.5.0 (4B multimodal, instruction-tuned)
Maintained by Google (Health AI Developer Foundations)1
MedGemma 1.5 4B is a multimodal, instruction-tuned update to MedGemma 1 4B, released by Google on January 13, 2026. It accepts text and images and produces text, adding support for CT and MRI volumes, whole-slide histopathology, longitudinal chest X-rays, anatomical localization, lab-report extraction, and text-based EHR interpretation.189
- Documentation: Model card (Health AI Developer Foundations) (external site: developers.google.com)
- Model hub: Hugging Face repository (external site: huggingface.co)
- Paper: MedGemma 1.5 Technical Report (arXiv 2604.05081) (external site: arxiv.org)
- License: Health AI Developer Foundations terms of use (external site: developers.google.com)
Availability and license
Overall availability
Downloadable from Hugging Face after logging in and acknowledging the Health AI Developer Foundations terms of use; the gate states that requests are processed immediately. Also offered through Google Cloud Model Garden.321
Availability is separate from permission: read the license before using or redistributing.
Health AI Developer Foundations Terms of Use (external site: developers.google.com)314
Apache License 2.0 (google-health/medgemma notebooks and serving code) (external site: raw.githubusercontent.com)56
The HAI-DEF terms (licensor Google LLC) permit use, modification, and distribution, including hosted services, subject to use restrictions: no uses listed in the HAI-DEF Prohibited Use Policy, no use that could lead a health regulator to deem Google a medical device manufacturer, and compliance with law. Redistributors must pass on the terms and the use restrictions, include a specified notice file, and seek health regulatory authorization where applicable. The terms define Model Derivatives to include models distilled from outputs, require indemnification of Google, allow Google to terminate for breach or regulatory risk, and are governed by California law.4
Model-disclosure tier
The model parameters for this release can be downloaded by the public. License terms may still restrict use, redistribution, or commercial use.
The weights are under a license that is not on the rubric's OSI-approved list. Read its terms before use.
Public materials checklist
| Item | Status | Notes and evidence |
|---|---|---|
| WeightsCan the general public download the model parameters for this release? | Public | Weights are on Hugging Face behind a click-through acknowledgment of the HAI-DEF terms that is processed automatically.32 |
| Inference codeIs code for running the model published? | Public | The card documents inference with Hugging Face Transformers (4.50.0 or later); the Hugging Face page also shows vLLM and SGLang serving. The google-health/medgemma repository publishes notebooks and serving-container code under Apache 2.0.125 |
| Training codeIs the code used to train the model published? | Unknown | The card states training was done with JAX; fine-tuning notebooks are published, but the code used to train the model was not found.15 |
| Training-data informationPublic = the training data itself can be obtained. Partial = composition or sources are documented without full access. | Partial | The card lists public datasets used (for example MIMIC-CXR, SLAKE, PAD-UFES-20, TCGA, CAMELYON, and PMC-OA) along with licensed or internally collected de-identified datasets that are not public.1 |
| Training recipeAre the training configuration and procedure documented in enough detail to follow? | Partial | The MedGemma 1.5 technical report describes the new training data, 3D volume slicing, and whole-slide sampling approaches at a summary level.7 |
| Evaluation materialsPublic = evaluation code or prompts that let others re-run the evaluations are published. Partial = results only. | Partial | The card publishes evaluation results on public and internal benchmarks; several evaluation datasets are internal.1 |
What it is useful for
Run and use notes
Organization context
Provenance and derivatives
An updated version of MedGemma 1 4B, built on Gemma 3 and its decoder-only architecture, with a SigLIP image encoder pre-trained on de-identified medical data.1
- Derived from: MedGemma 1 4B — Previous MedGemma 4B release; no separate catalog record.
- Derived from: Gemma 3 — Base model family; see the Gemma family record.
Other releases in the MedGemma family
- MedGemma 27B (multimodal)Model-disclosure tier (USASI rubric v0.1): Open-weight
U.S. eligibility
Eligible · basis: Documented U.S. control
The model card lists Google as author, and the governing terms are issued by Google LLC. Alphabet Inc.'s fiscal 2025 Form 10-K lists its principal executive offices in Mountain View, California, and Exhibit 21.01 lists Google LLC as a Delaware subsidiary of Alphabet.141011
Sources
This listing is not an endorsement, a safety assessment, or a federal approval.