> 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.

# Kimi-K2.5

> Use NeMo AutoModel to fine-tune Kimi-K2.5 for VLM workflows with checked-in image-text-to-text recipes and documented distributed settings.

[Kimi-K2.5](https://huggingface.co/moonshotai/Kimi-K2.5) has a checked-in NeMo AutoModel recipe for image-text-to-text.
The Hugging Face configuration declares the `KimiK25ForConditionalGeneration` architecture.

## Fine-Tune Kimi-K2.5

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

```bash
automodel examples/vlm_finetune/kimi/kimi25vl_medpix.yaml --nproc-per-node 8
```

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/vlm_finetune/kimi/kimi25vl_medpix.yaml). |
| Try another checked-in recipe for this model | Use the [alternate recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_benchmark/kimi/kimi25vl_lora.yaml).      |

### Configuration

| Setting  | Configuration                                                        |
| -------- | -------------------------------------------------------------------- |
| Hardware | -                                                                    |
| Strategy | FSDP2; tp\_size=1, pp\_size=8, cp\_size=1, ep\_size=32               |
| Nodes    | 32                                                                   |
| Features | Transformer Engine, DeepEP (dispatcher=deepep)                       |
| Advanced | bfloat16, attention=te, linear=torch, experts=gmm, dispatcher=deepep |

### More Recipes for This Model

* [`kimi25vl_lora.yaml`](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/vlm_benchmark/kimi/kimi25vl_lora.yaml)

## Model Reference

### Model Architecture

| Property     | Value                             |
| ------------ | --------------------------------- |
| Task         | Image-text-to-text                |
| Architecture | `KimiK25ForConditionalGeneration` |

### Available Models

* [`moonshotai/Kimi-K2.5`](https://huggingface.co/moonshotai/Kimi-K2.5)

## Related Resources

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