> 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-K3

> Use Kimi-K3 with NeMo AutoModel for vision-language fine-tuning, with documented checkpoints, runnable recipes, setup guidance, and model reference details.

[Kimi-K3](https://huggingface.co/moonshotai/Kimi-K3) is a Moonshot AI vision-language model with a MoonViT3d vision tower and a Kimi Linear Mixture-of-Experts language backbone.

Set up NeMo AutoModel with the [latest container](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo-automodel) or follow the [installation instructions](/get-started/installation).

## Fine-Tune Kimi-K3

From the repository root, run:

```bash
uv run automodel --nproc-per-node=8 examples/llm_finetune/kimi/k3_hellaswag.yaml
```

## Choose a Workflow

| Goal                                                             | Start Here                                                                                                                                     |
| ---------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- |
| Supervised fine-tuning (SFT) - text-only Kimi-K3 with EP32 + PP8 | Use [k3\_hellaswag.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/kimi/k3_hellaswag.yaml). Dataset: HellaSwag. |

## Model Reference

### Model Architecture

| Property                  | Value                                                 |
| ------------------------- | ----------------------------------------------------- |
| Task                      | Image-Text-to-Text / Text Generation                  |
| Architectures             | `KimiK3ForConditionalGeneration`, `KimiK3ForCausalLM` |
| Hugging Face Organization | [moonshotai](https://huggingface.co/moonshotai)       |

* `KimiK3ForConditionalGeneration` combines the MoonViT3d vision tower and multimodal projector with the Kimi Linear language backbone.
* `KimiK3ForCausalLM` exposes the text-only Kimi Linear backbone.

### Available Models

| Model   | HF ID                                                             |
| ------- | ----------------------------------------------------------------- |
| Kimi-K3 | [`moonshotai/Kimi-K3`](https://huggingface.co/moonshotai/Kimi-K3) |

## Related Resources

* [LLM Fine-Tuning Guide](/recipes-e2e-examples/sft-peft)
* [VLM Fine-Tuning Guide](/recipes-e2e-examples/gemma-3-3n)