> 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.

# Qwen3.6-35B-A3B

> Use NeMo AutoModel to fine-tune Qwen3.6-35B-A3B for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.

[Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) has a checked-in NeMo AutoModel recipe for image-text-to-text.
The Hugging Face configuration declares the `Qwen3_5MoeForConditionalGeneration` architecture.

## Fine-Tune Qwen3.6-35B-A3B

Follow the [installation instructions](/get-started/installation), then run the recipe from the repository root:

```bash
automodel examples/vlm_finetune/qwen3_5_moe/qwen3_6_35b.yaml --nproc-per-node 8
```

## Choose a Workflow

| Goal                                         | Start Here                                                                                                                              |
| -------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------- |
| Run the primary recipe for this model        | Use the [recipe configuration](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/qwen3_5_moe/qwen3_6_35b.yaml).  |
| Try another checked-in recipe for this model | Use the [alternate recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/qwen3_5_moe/qwen3_6_35b_lora.yaml). |

### Configuration

| Setting  | Configuration                                                                                                       |
| -------- | ------------------------------------------------------------------------------------------------------------------- |
| Hardware | -                                                                                                                   |
| Strategy | FSDP2; tp\_size=1, pp\_size=1, cp\_size=1, ep\_size=8                                                               |
| Nodes    | -                                                                                                                   |
| Features | Checkpointing (enabled=true), Activation checkpointing (activation\_checkpointing=true), DeepEP (dispatcher=deepep) |
| Advanced | attention=sdpa, linear=torch, experts=gmm, dispatcher=deepep                                                        |

### More Recipes for This Model

* [`qwen3_6_35b_lora.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/qwen3_5_moe/qwen3_6_35b_lora.yaml)
* [`qwen3_6_35b_medpix_ep8cp2_4k.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_finetune/qwen3_5_moe/qwen3_6_35b_medpix_ep8cp2_4k.yaml)

## Model Reference

### Model Architecture

| Property     | Value                                |
| ------------ | ------------------------------------ |
| Task         | Image-text-to-text                   |
| Architecture | `Qwen3_5MoeForConditionalGeneration` |

### Available Models

* [`Qwen/Qwen3.6-35B-A3B`](https://huggingface.co/Qwen/Qwen3.6-35B-A3B)

## Related Resources

* [Vision-language model fine-tuning guide](/recipes-e2e-examples/gemma-3-3n)