> 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.

# gemma-4-31B

> Fine-tune gemma-4-31B for text generation with NeMo AutoModel using checked-in recipes and documented distributed settings.

[Gemma-4-31B](https://huggingface.co/google/gemma-4-31B) has a checked-in NeMo AutoModel recipe for text generation.
The Hugging Face configuration declares the `Gemma4ForConditionalGeneration` architecture.

## Fine-Tune Gemma-4-31B

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.

Use the [Slurm launcher guide](/job-launchers/slurm-cluster) for the multi-node run.

## 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/gemma4-31b/gemma4_31b_tulu3_packed2k_cp1_gbs32_4node.yaml).  |
| Try another checked-in recipe for this model | Use the [alternate recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/long_context_validation/gemma4_31B/gemma4_31b_base_coderforge_cp8_64k_1e5_800steps.yaml). |

### Configuration

| Setting  | Configuration                                                                           |
| -------- | --------------------------------------------------------------------------------------- |
| Hardware | -                                                                                       |
| Strategy | FSDP2; tp\_size=1, cp\_size=1                                                           |
| Nodes    | 4                                                                                       |
| Features | Checkpointing (enabled=true), Activation checkpointing (activation\_checkpointing=true) |
| Advanced | torch.bfloat16                                                                          |

### More Recipes for This Model

* [`gemma4_31b_base_coderforge_cp8_64k_1e5_800steps.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/long_context_validation/gemma4_31B/gemma4_31b_base_coderforge_cp8_64k_1e5_800steps.yaml)

## Model Reference

### Model Architecture

| Property     | Value                            |
| ------------ | -------------------------------- |
| Task         | Text generation                  |
| Architecture | `Gemma4ForConditionalGeneration` |

### Available Models

* [`google/gemma-4-31B`](https://huggingface.co/google/gemma-4-31B)

## Related Resources

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