Sovereign 8s.is mirror of standardgalactic/medgemma
  • Jupyter Notebook 97.6%
  • Python 2.4%
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
tiffchen ca633909d4
Update Model Garden quick start notebook.
* Add Google Colab compatibility
* Add checks for MedGemma DICOM endpoints, which are not OpenAI-compatible and do not support streaming at this time

PiperOrigin-RevId: 856942653
2026-01-16 04:50:32 +00:00
.github Initial commit 2025-05-20 08:59:33 -07:00
notebooks Update Model Garden quick start notebook. 2026-01-16 04:50:32 +00:00
python Release MedGemma 1.5. 2026-01-13 20:48:30 +00:00
CONTRIBUTING.md Initial commit 2025-05-20 08:59:33 -07:00
LICENSE Initial commit 2025-05-20 08:59:33 -07:00
README.md Initial commit 2025-05-20 08:59:33 -07:00

MedGemma

MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension. Developers can use MedGemma to accelerate building healthcare-based AI applications. MedGemma comes in two variants: a 4B multimodal version and a 27B text-only version.

MedGemma 4B utilizes a SigLIP image encoder that has been specifically pre-trained on a variety of de-identified medical data, including chest X-rays, dermatology images, ophthalmology images, and histopathology slides. Its LLM component is trained on a diverse set of medical data, including radiology images, histopathology patches, ophthalmology images, dermatology images, and medical text.

MedGemma variants have been evaluated on a range of clinically relevant benchmarks to illustrate their baseline performance. These include both open benchmark datasets and curated datasets, with a focus on expert human evaluations for tasks. Developers can fine tune MedGemma variants for improved performance. Please read more about our work in our manuscript [link coming] and consult our Intended Use Statement for more details.

Get started

Contributing

We are open to bug reports, pull requests (PR), and other contributions. See CONTRIBUTING and community guidelines for details.

License

While the model is licensed under the Health AI Developer Foundations License, everything in this repository is licensed under the Apache 2.0 license, see LICENSE.