> ## 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 train the following models:

* `nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B`
* `google/gemma-4-26B-A4B-it`
* `meta-llama/Llama-3.1-8B-Instruct`
* `Qwen/Qwen3.6-35B-A3B`
* `Qwen/Qwen3.8-27B`

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

The UI lists a model only while the training service accepts it, so a model can temporarily disappear from the selector.

## Experimental models

The following models are available on request as experimental training targets. They might not appear in your model selector by default, and support can change without notice.

* `Qwen/Qwen3.5-4B`
* `Qwen/Qwen3.5-9B`
* `google/gemma-4-31B-it`

> [!NOTE]
>
> These lists apply to models you can train. You can also connect existing models from OpenAI-compatible providers for serving, relabeling, and comparison.

## You do not need to choose one model in advance

Train a few promising models, evaluate them against the behavior you want, and deploy the strongest result. This lets you compare results for your task instead of choosing a model based only on benchmarks or size.

> [accordion] API: Use model IDs
>
> When you create a fine-tune, copy a listed value exactly into `base_model`:
>
> ```json theme={"system"}
> {"base_model": "Qwen/Qwen3.6-35B-A3B"}
> ```
>
> Use the complete request in [Fine-tuning quick start](https://docs.coreweave.com/model-distillation/studio/fine-tuning-quickstart.md).
