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

# Optimized Models Catalog

> Browse, buy, download, and deploy verified optimized model packages with measured performance and quality receipts.

The Optimized Models Catalog contains verified optimized model packages for open-weight models. Each package combines one model, one target GPU, and one serving engine. RunInfra quantizes and serving-tunes that combination, then publishes its measured speedup, throughput, accuracy recovery, and VRAM receipt.

<Info>
  Measurements apply to the model, GPU, and serving engine named on the package page. Review that page before buying instead of assuming the same results for another configuration.
</Info>

## What a package includes

| Included item         | What you get                                                                         |
| --------------------- | ------------------------------------------------------------------------------------ |
| Optimized weights     | The quantized model weights for the listed package.                                  |
| Serving configuration | The exact configuration used for the package's serving engine and target GPU.        |
| Measured proof        | The recorded speedup, throughput, accuracy recovery, and VRAM results.               |
| Deploy guides         | Instructions for Docker, Docker Compose, Kubernetes, RunPod, and Modal.              |
| License files         | The RunInfra package license and the base model's upstream license with attribution. |

## Browse the catalog

Browse the public catalog at [runinfra.ai/catalog](https://runinfra.ai/catalog). Each model has a public page at `/catalog/<slug>` with:

* Measured proof charts
* Package specifications, including the target GPU and serving engine
* A provider comparison
* Package and base model license information
* A shareable model card

The measured figures vary by package. Use the figures on the model page as the source of truth for that package.

## Buy a package

<Steps>
  <Step title="Review the package">
    Confirm the model, target GPU, serving engine, measured receipt, and both licenses on the model page.
  </Step>

  <Step title="Check your workspace credits">
    Packages use your existing workspace credit balance, where 1 credit = \$1. Your workspace must have a paid plan before it can spend credits on a package.
  </Step>

  <Step title="Complete the one-time purchase">
    The package belongs to the purchasing workspace. It never expires, and you can download it again at any time.
  </Step>
</Steps>

<Note>
  [Continuous Optimization](/docs/features/continuous-optimization) is an optional monthly subscription. It is separate from the one-time package purchase.
</Note>

## Download the kit

After purchase, download the self-contained kit from the package page. It contains the optimized weights, exact serving configuration, measured proof, license files, and deployment guides.

The kit does not call home. You can run it on the package's target GPU in any cloud or on your own hardware.

## Deploy the package

Choose the included guide for your environment:

| Target         | Use it for                                          |
| -------------- | --------------------------------------------------- |
| Docker         | Running the package as a container on one host.     |
| Docker Compose | Starting the included local stack with one command. |
| Kubernetes     | Running the package in your cluster.                |
| RunPod         | Running the package on your RunPod GPU.             |
| Modal          | Running the package on Modal.                       |

For the Docker Compose quickstart, unzip the kit and open its directory. Then set `VLLM_API_KEY` and start the included Compose configuration:

<Tabs>
  <Tab title="macOS and Linux">
    ```bash theme={"dark"}
    export VLLM_API_KEY="<your-api-key>"
    docker compose up
    ```
  </Tab>

  <Tab title="Windows PowerShell">
    ```powershell theme={"dark"}
    $env:VLLM_API_KEY = "<your-api-key>"
    docker compose up
    ```
  </Tab>
</Tabs>

After the service starts, use the exact endpoint from the included guide:

```bash theme={"dark"}
curl <local-endpoint-from-the-guide> \
  -H "Authorization: Bearer <your-api-key>"
```

<Tip>
  Keep the model, GPU, serving engine, and serving configuration together. The receipt describes that measured combination.
</Tip>

## Understand the licenses

Two licenses apply to every package:

| License                      | What it allows and requires                                                                                                                    |
| ---------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- |
| **RunInfra package license** | Unlimited production use within the purchasing workspace. You can sell outputs produced with the package. You cannot redistribute the package. |
| **Base model license**       | The upstream open-source license for the original model, such as Apache-2.0. It ships inside the kit with the required attribution.            |

You must follow both licenses. Buying a package does not replace or override the base model's upstream terms.

## Request a model

If the catalog does not include the combination you need, submit a request with:

* Model
* GPU
* Target
* Serving engine

RunInfra uses request volume to decide which combinations to optimize next. The most-requested combinations move to the front of the catalog queue.

## Catalog packages and custom optimization

The catalog gives you a prebuilt package for a listed model, GPU, and serving engine. Use [Optimization](/docs/features/optimization) when you want RunInfra to measure and rank variants for your own pipeline and constraints. See [Models](/docs/features/models) for the broader set of models RunInfra can resolve and deploy.

## Next steps

<Columns cols={2}>
  <Card title="Continuous Optimization" icon="refresh-cw" href="/docs/features/continuous-optimization">
    Keep a purchased package current with newly verified versions.
  </Card>

  <Card title="Models" icon="cpu" href="/docs/features/models">
    Browse the model types RunInfra supports.
  </Card>

  <Card title="Optimization" icon="zap" href="/docs/features/optimization">
    Measure and rank variants for your own pipeline.
  </Card>

  <Card title="Plans and pricing" icon="credit-card" href="/docs/introduction/plans">
    Learn how workspace credits and paid plans work.
  </Card>
</Columns>