> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/clara/parabricks/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/clara/parabricks/_mcp/server.

# Get Started

This section describes what you need to know to get started with Parabricks and
how to make the best use of your hardware.

* The [Installation Requirements](/get-started/installation-requirements) section covers both hardware and software requirements.
* The [Getting the Parabricks Docker Image](/get-started/deploy-nvidia-parabricks#getting-the-parabricks-docker-image) section describes how to get Parabricks.
  Parabricks is delivered as a Docker container so getting it is as simple as a `docker pull` command.
* [Running NVIDIA Parabricks](/get-started/deploy-nvidia-parabricks#running-nvidia-parabricks) covers the basics of running Parabricks
  along with the more common Docker options used.
* [Getting the Best Performance](/get-started/getting-the-best-performance) covers how to get the optimal performance
  out of your GPU.
* [NVIDIA Grace CPU Platforms](/get-started/nvidia-grace-cpu-platforms) discusses the key features and advantages of the NVIDIA Grace CPU Platforms.

The [Genomics Analysis AI Blueprint](https://build.nvidia.com/nvidia/genomics-analysis) lets you try Parabricks on popular cloud platforms with automatic environment setup.