> 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.

# Qwen3-8B

> Convert and fine-tune Qwen3-8B as a diffusion language model with NeMo AutoModel using the checked-in I-DLM recipe and text checkpoint.

The I-DLM recipe converts the autoregressive [`Qwen/Qwen3-8B`](https://huggingface.co/Qwen/Qwen3-8B) checkpoint into a diffusion language model using an all-masked block-diffusion objective.

## Fine-Tune Qwen3-8B

From the repository root, run:

```bash
uv run torchrun --nproc-per-node=8 nemo_automodel/recipes/dllm/train_ft.py \
  -c examples/dllm_sft/qwen3_8b_idlm.yaml
```

## Model Reference

### Model Architecture

| Property         | Value                                       |
| ---------------- | ------------------------------------------- |
| **Task**         | Diffusion Language Modeling                 |
| **Architecture** | `Qwen3ForCausalLM` with the I-DLM objective |
| **Parameters**   | 8B                                          |
| **HF Org**       | [Qwen](https://huggingface.co/Qwen)         |

## Example Model and Recipe

| Model                                                   | Recipe                                                                                                            |
| ------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------- |
| [`Qwen/Qwen3-8B`](https://huggingface.co/Qwen/Qwen3-8B) | [I-DLM full fine-tuning](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/dllm_sft/qwen3_8b_idlm.yaml) |

See the [dLLM Fine-Tuning Guide](/recipes-e2e-examples/dllm-fine-tuning).