You can get started in 4 ways:

## Run it locally

Download the MedGemma model you are interested in from [Hugging
Face](https://huggingface.co/collections/google/medgemma-release-680aade845f90bec6a3f60c4)
and run it locally.

This is the recommended option if you want to experiment with MedGemma and don't
need to handle a high volume of data. Note to run the 27B model without
quantization you will need to use [Colab
Enterprise](https://cloud.google.com/colab/docs/introduction). Our GitHub
repository includes a
[notebook](https://github.com/google-health/medgemma/blob/main/notebooks/quick_start_with_hugging_face.ipynb)
that you can use to explore the model.

## Deploy your own online service

MedGemma can be deployed as a highly available and scalable HTTPS endpoint on
[Vertex AI](https://cloud.google.com/vertex-ai). The easiest way is through
[Model
Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/medgemma).

This option is ideal for production-grade, online applications with low latency,
high scalability and availability requirements. Refer to [Vertex AI's service
level agreement (SLA)](https://cloud.google.com/vertex-ai/sla) and [pricing
model](https://cloud.google.com/vertex-ai/pricing) for online predictions.

A sample
[notebook](https://github.com/google-health/medgemma/blob/main/notebooks/quick_start_with_model_garden.ipynb)
is available to help you get started quickly.

## Fine-tune MedGemma

MedGemma can be fine-tuned using your own medical data to optimize its
performance for your use cases. A sample
[notebook](https://github.com/google-health/medgemma/blob/main/notebooks/fine_tune_with_hugging_face.ipynb)
is available that you can adapt for your data and use case.

## Launch a batch job

For larger datasets in a batch workflow, it's best to launch it as a [Vertex AI
batch prediction
job](https://cloud.google.com/vertex-ai/docs/predictions/get-batch-predictions#request_a_batch_prediction).
Note that [Vertex AI's SLA](https://cloud.google.com/vertex-ai/sla) and [pricing
model](https://cloud.google.com/vertex-ai/pricing) are different for batch
prediction jobs.

## Engage with us

Here are the best ways to engage with our team and the community:

- **Feature your work** on the [HAI-DEF
  Showcase](https://developers.google.com/health-ai-developer-foundations/showcase) using the [intake
  form](https://services.google.com/fb/forms/hai-def-showcase/).
- **Help shape our roadmap** by sharing your use cases using our [feedback
  form](https://services.google.com/fb/forms/hai-def-feedback/). This helps us align our engineering efforts with the industry's most common needs.
- **Stay in the know** on new tools and models by signing up for [our
  newsletter](https://services.google.com/fb/forms/hai-def-news/).
- **Seek technical support** on the [HAI-DEF developer
  forum](https://discuss.ai.google.dev/c/hai-def/).
- **File technical issues** directly on [GitHub](https://github.com/Google-Health/medgemma/issues).