> This page is for version 1.0.0 (Latest) (default).
> For other versions, use one of these documentation indexes:
> - 1.0.0 (Latest) (default): https://docs.nvidia.com/nim/harmonizer/1.0.0/llms.txt

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

# About Get Started with Harmonizer NIM

> Choose a Docker or Kubernetes deployment path and prepare to run your first Harmonizer inference request.

Before deploying Harmonizer NIM, review the GPU, software, and access
requirements in [Harmonizer NIM Prerequisites](/nim/harmonizer/prerequisites).

## Choose Your Path

Select a guide based on your deployment environment and goal.

| Audience                              | Starting Point                                                                                                                               |
| ------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
| Application developers and evaluators | Use the [Quickstart Guide](/nim/harmonizer/quickstart-guide) to launch one container and send an HTTP or gRPC inference request.             |
| Kubernetes platform operators         | Use [Deploy Harmonizer NIM with Helm](/nim/harmonizer/helm) to configure the shared NIM chart, launch Harmonizer, and verify the deployment. |

#### [Quickstart](/nim/harmonizer/quickstart-guide)

Launch Harmonizer with Docker, check readiness, and run inference.

#### [Deploy with Helm](/nim/harmonizer/helm)

Deploy Harmonizer to Kubernetes with the production NIM for World
Foundation Models (WFM) chart.