> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/installation-and-configuration/system-requirements/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** 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. 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. ## Docs - [Deployment Model](https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/installation-and-configuration/system-requirements/deployment-model.md) - [Infrastructure Requirements](https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/installation-and-configuration/system-requirements/infrastructure-requirements.md) - [Networking Setup](https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/installation-and-configuration/system-requirements/networking-setup.md) - [Standard Third-Party Services](https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/installation-and-configuration/system-requirements/third-party-services/standard-third-party-services.md) - [Gov-Ready Third-Party Services](https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/installation-and-configuration/system-requirements/third-party-services/gov-ready-third-party-services.md) - [External Access to Critical Services](https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/installation-and-configuration/system-requirements/external-access-to-critical-services.md)