> 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.

# Qwen3-4B-Base

> Use NeMo AutoModel to fine-tune Qwen3-4B-Base for LLM workflows with checked-in text generation recipes and documented distributed settings.

[Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) has a checked-in NeMo AutoModel recipe for text generation.
The Hugging Face configuration declares the `Qwen3ForCausalLM` architecture.

## Fine-Tune Qwen3-4B-Base

Follow the [installation instructions](/get-started/installation), then review the checked-in recipe and
its declared topology below before choosing a local or cluster launcher.

## 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/convergence/tulu3/models/qwen3-4b/qwen3_4b_cp1_flashoptim.yaml). |
| Try another checked-in recipe for this model | Use the [alternate recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/convergence/tulu3/models/qwen3-4b/qwen3_4b_cp1_te_fusedadam.yaml).   |

### Configuration

| Setting  | Configuration                                                                           |
| -------- | --------------------------------------------------------------------------------------- |
| Hardware | -                                                                                       |
| Strategy | FSDP2; tp\_size=1, pp\_size=1, cp\_size=1                                               |
| Nodes    | -                                                                                       |
| Features | Checkpointing (enabled=true), Activation checkpointing (activation\_checkpointing=true) |
| Advanced | sequence length 2048                                                                    |

### More Recipes for This Model

* [`qwen3_4b_cp1_te_fusedadam.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/convergence/tulu3/models/qwen3-4b/qwen3_4b_cp1_te_fusedadam.yaml)
* [`qwen3_4b_cp2_flashoptim.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/convergence/tulu3/models/qwen3-4b/qwen3_4b_cp2_flashoptim.yaml)

## Model Reference

### Model Architecture

| Property     | Value              |
| ------------ | ------------------ |
| Task         | Text generation    |
| Architecture | `Qwen3ForCausalLM` |

### Available Models

* [`Qwen/Qwen3-4B-Base`](https://huggingface.co/Qwen/Qwen3-4B-Base)

## Related Resources

* [LLM fine-tuning guide](/recipes-e2e-examples/sft-peft)