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

# Supported Models

> Train open source models on ART.

## Serverless Models

We currently only support the following model for serverless training. We are actively adding support for both larger and smaller models. If there's a particular model you'd like to see serverless support for, please send a request to [support@wandb.com](mailto:support@wandb.com).

* [OpenPipe Qwen 3 14B Instruct](https://huggingface.co/OpenPipe/Qwen3-14B-Instruct)
  * Good balance of performance and size. Has support for tool calling and generally trains well. This is our recommended model for users new to RL.
* [Qwen 3 30B A3B Instruct](https://huggingface.co/Qwen/Qwen3-30B-A3B)
  * More capable than 14B while still being efficient. Good choice when you need stronger reasoning capabilities.

## Recommended Local Models

If you're developing locally or in your own hardware, here are a couple other models you could try in addition to the recommended serverless list.

* [Qwen2.5 7B Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
  * Less capable than 14B, but smaller and faster
* [Qwen2.5 32B Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct)
  * More capable than 14B, but larger and slower

## More Models

ART has wide support for models supported by [vLLM](https://docs.vllm.ai/en/latest/models/supported_models.html). However, not all models support all features. For instance, if a model's chat template does not include tool call support, you won't be able to use tools with it natively. And if a model's architecture doesn't have support for LoRA layers, it won't be compatible with our LoRA-based backend, but still may work with our full-fine-tuning backend.

Here are additional models that we've tested and found to work well with ART:

* [Llama 3.1 8B Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)
* [Llama 3.2 1B Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)
* [Llama 3.2 3B Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
* [Llama 3.3 70B Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct)
* [Qwen2.5 72B Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)
* Additionally, the [Qwen 3](https://huggingface.co/collections/Qwen/qwen3-67dd247413f0e2e4f653967f) family of models is well supported for single-turn workflows. For multi-turn workflows the Qwen 3 chat template removes the `<think>` tokens from previous turns, which makes training more complicated. It is still possible to use for multi-turn workflows by splitting each turn into a separate message history with our `additional_histories` trajectory parameter (see [Additional Histories](/features/additional-histories)).

If you're curious about a model that is not listed above, ask in the Discord [#support](https://discord.com/channels/1359674493949448375/1359674622965973185) channel.