Services

Run open-source large language models locally

AILLM
Deploy

What is Ollama?

Ollama is a tool for downloading, managing, and running open-weight LLMs on local machines or servers. It provides a CLI, REST API, and model library for chat, coding, vision, and embedding models. Ollama is designed to make local inference simple without requiring manual model setup for each application.

How to deploy on Kubeara

  1. Sign in to your Kubeara dashboard and connect a server if you have not already.

  2. Open the Services catalog and select Ollama.

    Ollama on Kubeara
    Ollama on Kubeara
  3. Review the pre-configured settings and click Deploy.

    Ollama environment configuration on Kubeara
    Ollama environment configuration on Kubeara
  4. Ollama is now running on your Kubeara server. Open your dashboard to get started.