> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ramalama.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Cloud

> Using RamaLama Labs container artifacts in the cloud.

Our containerized AI artifacts are OCI compatible allowing you to directly use them with docker, podman and kubernetes wherever you need them: whether the cloud, a datacenter, or your basement.
Our artifacts are regularly rebuilt, updated, and scanned for vulnerabilities to provide, the smallest, fastest, and most secure runtime possible.

<Tip>
  You can find comparisons between different images on the comparisons page of each image
  (e.g. for llama.cpp's [cuda](https://registry.ramalama.com/projects/ramalama/repositories/ramalama%2Fllamacpp-cuda-distroless) and [cpu](https://registry.ramalama.com/projects/ramalama/repositories/ramalama%2Fllamacpp-cpu-distroless)) runtimes.
</Tip>

## Quick start

The fastest path is to deploy a model image that bundles runtime + model using docker compose.
For more information about deploying in production environments check out [deployment](/pages/deploying/compose.mdx).

<Steps>
  <Step title="Install dependencies">
    Getting started requires either Docker or Podman. We also recommend the RamaLama CLI for a streamlined experience.

    1. Install [Podman](https://podman.io/docs/installation) or [Docker](https://docs.docker.com/get-docker/)
    2. (Optional) Install [RamaLama CLI](/pages/getting_started/oss)
  </Step>

  <Step title="Create docker-compose.yaml">
    Create a `docker-compose.yaml` using a model image which bundles both the runtime and model together into a single runnable container.

    <CodeGroup>
      ```yaml theme={"system"}
      services:
        ai:
          image: rlcr.io/ramalama/gemma3-270m:latest
          ports:
              - "8080:8080"
          restart: unless-stopped
      ```
    </CodeGroup>
  </Step>

  <Step title="Start the stack">
    <CodeGroup>
      ```bash title="Docker" theme={"system"}
      docker compose up -d
      ```

      ```bash title="Podman" theme={"system"}
      podman compose up -d
      ```
    </CodeGroup>
  </Step>

  <Step title="Get chatting">
    <CodeGroup>
      ```bash title="curl" theme={"system"}
      curl -s http://localhost:8080/v1/chat/completions \
          -H 'Content-Type: application/json' \
          -d '{"model":"gemma3-270m","messages":[{"role":"user","content":"Say hello in one sentence"}]}'
      ```

      ```bash title="RamaLama" theme={"system"}
      ramalama chat "Say hello in one sentence"
      ```
    </CodeGroup>

    <CodeGroup>
      ```text title="RamaLama" theme={"system"}
      Hello!
      ```

      ```json title="curl" theme={"system"}
      {
          "id":"chatcmpl-ZYtHxmjGSdIHs7tqMlA6eS9NhctuDZ6Y",
          "model":"gemma3-270m",
          "object":"chat.completion",
          "choices":[{"finish_reason":"stop","index":0,"message":{"role":"assistant","content":"Hello! "}}]
      }
      ```
    </CodeGroup>
  </Step>
</Steps>