> This page is for Self-Hosted, version v3.0 (default).
> For other versions, use one of these documentation indexes:
> - v3.0 (default): https://docs.nvidia.com/run-ai/self-hosted/v3.0/llms.txt
> - v2.26: https://docs.nvidia.com/run-ai/self-hosted/v2.26/llms.txt
> - v2.25: https://docs.nvidia.com/run-ai/self-hosted/v2.25/llms.txt
> - v2.24: https://docs.nvidia.com/run-ai/self-hosted/v2.24/llms.txt

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

# System Requirements

This section describes the infrastructure you must provide before installing NVIDIA Run:ai - hardware, Kubernetes distribution, networking, and storage - and the third-party services the installation deploys for you, whether you use the [Guided Installation](/run-ai/self-hosted/documentation/installation-and-configuration/install/guided-installation) or [Manual Helm](/run-ai/self-hosted/documentation/installation-and-configuration/install/manual-helm/preparations) path. It follows the [shared responsibility model](/run-ai/self-hosted/documentation/installation-and-configuration/overview#shared-responsibility): NVIDIA provides the Run:ai software, while you prepare and manage the Kubernetes environment it runs on.

<Note>

**Note**

Before reviewing the requirements, determine your [deployment model](/run-ai/self-hosted/documentation/installation-and-configuration/system-requirements/deployment-model), as it affects which infrastructure components must be provisioned once and which are required for each NVIDIA Run:ai cluster.

</Note>

Complete each of the following before installing NVIDIA Run:ai:

| Section | What to prepare |
|---|---|
| [Deployment Model](/run-ai/self-hosted/documentation/installation-and-configuration/system-requirements/deployment-model) | Same-cluster vs multi-cluster connectivity, networking, DNS, and TLS requirements |
| [Infrastructure Requirements](/run-ai/self-hosted/documentation/installation-and-configuration/system-requirements/infrastructure-requirements) | Hardware, OS, Kubernetes distribution, storage, and permissions |
| [Networking Setup](/run-ai/self-hosted/documentation/installation-and-configuration/system-requirements/networking-setup) | Load balancer, ingress controller, DNS, FQDN, and TLS certificates |
| [Third-Party Services](/run-ai/self-hosted/documentation/installation-and-configuration/system-requirements/third-party-services/standard-third-party-services) | Services deployed as part of installation, their registries, and how to replace them with externally managed instances |
| [External Access to Critical Services](/run-ai/self-hosted/documentation/installation-and-configuration/system-requirements/external-access-to-critical-services) | Inbound/outbound firewall rules and registry domain allowlist |

## Next Steps

Once your environment is prepared, proceed to installation:

* [Guided Installation](/run-ai/self-hosted/documentation/installation-and-configuration/install/guided-installation) - Recommended for most installations.
* [Manual Helm](/run-ai/self-hosted/documentation/installation-and-configuration/install/manual-helm/preparations) - For organizations managing releases through their own tooling.