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

# Open Source Models

> Deploy off-the-shelf open source models or bring your own trained models.

<Info>
  This feature is on the roadmap. Today, only models trained on the platform can be deployed.
</Info>

## What's planned

* **Deploy off-the-shelf OSS models** — run popular open source models on dedicated GPUs without going through training. Pick a model, select your instance, and deploy.
* **Bring your own trained models** — deploy models you've already fine-tuned outside the platform. Upload your weights and serve them on the same infrastructure.

## Why this matters

Not every deployment starts with training on the Inference platform. Some teams want dedicated GPU serving for an existing open source model, or they've already fine-tuned a model elsewhere and want to host it. This feature will bring all of that into the same deployment workflow — same API, same monitoring, same scaling options.

<Card title="Want early access?" icon="envelope" href="https://inference.net/meet-with-us/">
  Talk to our team if you'd like to be notified when open source and custom model deployments are available.
</Card>