Skip to content
Skip to documentation content
Browse documentation
In progress Page being written

Quickstart on Minikube

Run LLMKube end-to-end on a local Minikube cluster, no cloud account required. The shortest path from a fresh laptop to a working OpenAI-compatible endpoint.

What this page will cover

  • System requirements (4+ CPUs, 8 GB RAM, 20 GB disk) and tooling install for macOS, Linux, and Windows.
  • Starting Minikube with the right resource flags so the operator and a small model both fit.
  • Installing the LLMKube operator with Helm and verifying the controller is healthy.
  • Deploying a TinyLlama or Phi-3 model from the catalog and port-forwarding to test the API.
Read the source on GitHub
LLMKube LLMKube

Kubernetes for Local LLMs. Deploy, manage, and scale AI inference workloads with production-grade orchestration.

© 2026 Defilan Technologies LLC

Community

Built for the Kubernetes and AI communities

LLMKube is not affiliated with or endorsed by the Cloud Native Computing Foundation or the Kubernetes project. Kubernetes® is a registered trademark of The Linux Foundation.