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

# Models you can train

> Train several model families and find the best quality, cost, and latency tradeoff for your task.

You can currently train:

* `OpenPipe/Qwen3-14B-Instruct`
* `Qwen/Qwen3.6-27B`
* `Qwen/Qwen3-30B-A3B-Instruct-2507`
* `meta-llama/Llama-3.1-8B-Instruct`

The best model depends on your task. A smaller model may be faster and cheaper, while a larger model may handle more difficult behavior. Model Distillation makes it practical to train several candidates and compare them on the same examples.

<Note>
  This list applies to models you can train. You can also connect existing models from OpenAI-compatible providers for serving, relabeling, and comparison.
</Note>

## You do not need to choose one model upfront

Train a few promising models, evaluate them against the behavior you want, and deploy the strongest result. This is often more reliable than choosing a model based only on benchmarks or size.

[Automation](/model-distillation/studio/automation) can run this search for you by training multiple candidates and promoting only a model that meets your quality goal.

<Accordion title="API: Use model IDs">
  Copy a listed value exactly into `base_model` when creating a fine-tune, or add one model object per candidate in Automation:

  ```json theme={"system"}
  {
    "models": [
      {"base_model": "Qwen/Qwen3.6-27B"},
      {"base_model": "meta-llama/Llama-3.1-8B-Instruct"}
    ]
  }
  ```

  Use the complete requests in [Fine-tuning Quick Start](/model-distillation/studio/fine-tuning-quickstart) or [Automation](/model-distillation/studio/automation).
</Accordion>