Is this page helpful?

Installation#

Before running a NIM VLM container, configure your environment and pull the container image. Most public NIM images currently support keyless access from NGC, so logging in to Docker is optional unless your image, tag, or model artifact requires credentials.

Docker Login#

If you created an NGC API key, authenticate with the NVIDIA Container Registry using the following command:

echo "$NGC_API_KEY" | docker login nvcr.io --username '$oauthtoken' --password-stdin

Use $oauthtoken as the username and NGC_API_KEY as the password. The $oauthtoken username is a special name that indicates you are authenticating with an API key, not a username and password.

Pull the Container Image#

Use docker pull to fetch the NIM container image. For eligible public-catalog NIMs, you can pull the image without logging in to Docker.

Authentication is required only for the following:

  • A Production Branch (PB) NIM

  • A NIM released before NIM VLM version 2.0.10-variant

  • A private or gated NIM image or model artifact

To fetch a model-specific NIM container from the NGC registry, use the model’s exact image tag. For example, for Gemma 4 31B IT:

docker pull nvcr.io/nim/google/gemma-4-31b-it:2.0.10-variant

Note

The exact image tag will vary depending on the container type and backend you intend to deploy. Check the Support Matrix for the model ID and version to use in the pull command for your preferred NVIDIA NIM container or model.