> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/automodel/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/automodel/_mcp/server.

# Qwen3-30B-A3B

> Use Qwen3-30B-A3B with NeMo AutoModel for language model fine-tuning, with documented checkpoints, runnable recipes, setup guidance, and model reference details.

[Qwen3 MoE](https://qwenlm.github.io/blog/qwen3/) is the Mixture-of-Experts variant of the Qwen3 series from Alibaba Cloud, activating a small fraction of parameters per token for efficient large-scale training.

Set up NeMo AutoModel with the [latest container](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo-automodel) or follow the [installation instructions](/get-started/installation).

## Fine-Tune Qwen3-30B-A3B

From the repository root, run:

```bash
uv run automodel --nproc-per-node=8 examples/llm_finetune/qwen/qwen3_moe_30b_te_deepep.yaml
```

## Choose a Workflow

| Goal                                                          | Start Here                                                                                                                                          |
| ------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------- |
| Supervised fine-tuning (SFT) - Qwen3 MoE 30B with TE + DeepEP | Use [qwen3\_moe\_30b\_te\_deepep.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/qwen/qwen3_moe_30b_te_deepep.yaml). |
| Low-rank adaptation (LoRA) - Qwen3 MoE 30B                    | Use [qwen3\_moe\_30b\_lora.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/qwen/qwen3_moe_30b_lora.yaml).            |

## Model Reference

### Model Architecture

| Property                  | Value                               |
| ------------------------- | ----------------------------------- |
| Task                      | Text Generation (MoE)               |
| Architecture              | `Qwen3MoeForCausalLM`               |
| Parameters                | 30B total / 3B active               |
| Hugging Face Organization | [Qwen](https://huggingface.co/Qwen) |

### Available Models

| Model         | HF ID                                                             |
| ------------- | ----------------------------------------------------------------- |
| Qwen3 30B A3B | [`Qwen/Qwen3-30B-A3B`](https://huggingface.co/Qwen/Qwen3-30B-A3B) |

## Related Resources

* [LLM Fine-Tuning Guide](/recipes-e2e-examples/sft-peft)
* [Large MoE Fine-Tuning Guide](/recipes-e2e-examples/large-moe-fine-tuning)