> This page is for version Nightly (default).
> For other versions, use one of these documentation indexes:
> - Nightly (default): https://docs.nvidia.com/nemo/automodel/nightly/llms.txt
> - Latest: https://docs.nvidia.com/nemo/automodel/latest/llms.txt
> - 0.5.0 · 26.06: https://docs.nvidia.com/nemo/automodel/v0.5/llms.txt
> - 0.4.0 · 26.04: https://docs.nvidia.com/nemo/automodel/v0.4/llms.txt

> 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.

# Tutorials

> Follow NeMo AutoModel walkthroughs for specific language, vision-language, multimodal, and audio models and tasks.

Tutorials walk through a specific model or task, including its data, training configuration, and launch steps. Choose a tutorial below or browse the model groups in the sidebar.

For instructions on adapting a training workflow across models, use [Training Recipes](/recipes-e2e-examples/overview). For support details and available configurations, use [Model Coverage](/model-coverage/overview).

## Large Language Models

| Tutorial                                                                      | Focus                                          |
| ----------------------------------------------------------------------------- | ---------------------------------------------- |
| [Function Calling with FunctionGemma](/recipes-e2e-examples/function-calling) | Fine-tune for function calling                 |
| [Multi-Turn Agent SFT](/recipes-e2e-examples/agent-sft)                       | Train on multi-turn tool-calling conversations |
| [NanoGPT Pretraining](/recipes-e2e-examples/nanogpt-pretraining)              | Pretrain a GPT model                           |
| [DeepSeek-V4 Flash](/recipes-e2e-examples/deepseek-v4-flash)                  | Fine-tune DeepSeek-V4 Flash                    |
| [Hy3-preview](/recipes-e2e-examples/hy3-preview)                              | Fine-tune Hy3-preview                          |
| [Nemotron-3-Ultra-550B](/recipes-e2e-examples/nemotron-3-ultra)               | Fine-tune Nemotron-3-Ultra                     |
| [DiffusionGemma](/recipes-e2e-examples/diffusiongemma)                        | Fine-tune a diffusion language model           |

## Vision and Multimodal Models

| Tutorial                                                                                                          | Focus                                      |
| ----------------------------------------------------------------------------------------------------------------- | ------------------------------------------ |
| [Gemma 3 / 3n](/recipes-e2e-examples/gemma-3-3n)                                                                  | Fine-tune Gemma 3 and Gemma 3n             |
| [Gemma 4 31B](/recipes-e2e-examples/gemma-4)                                                                      | Fine-tune Gemma 4                          |
| [Qwen3.5-VL](/recipes-e2e-examples/qwen3-5-vl)                                                                    | Fine-tune Qwen3.5 vision-language models   |
| [Qwen3.8-27B](/recipes-e2e-examples/qwen3-8-27b)                                                                  | Run full SFT or LoRA on MedPix-VQA         |
| [Nemotron-Omni](/recipes-e2e-examples/nemotron-omni)                                                              | Fine-tune Nemotron-Omni                    |
| [Nemotron 3.5 Super VL](/recipes-e2e-examples/nemotron-3-5-super-vl)                                              | Fine-tune Nemotron 3.5 Super VL            |
| [Nemotron 3.5 Super VL: Text-to-SQL](/recipes-e2e-examples/nemotron-3-5-super-vl-text-to-sql)                     | Adapt the model with LoRA                  |
| [Nemotron 3.5 Super VL: Continued Pretraining](/recipes-e2e-examples/nemotron-3-5-super-vl-continued-pretraining) | Continue pretraining on FineWeb            |
| [Mistral Medium 3.5 VL](/recipes-e2e-examples/mistral-medium-3-5)                                                 | Fine-tune Mistral Medium 3.5               |
| [MiniMax-M3](/recipes-e2e-examples/minimax-m3)                                                                    | Fine-tune MiniMax-M3 with full SFT or LoRA |
| [Step-3.7-Flash](/recipes-e2e-examples/step-3-7)                                                                  | Fine-tune Step-3.7-Flash                   |

## Audio

| Tutorial                                                    | Focus                                      |
| ----------------------------------------------------------- | ------------------------------------------ |
| [ASR with Qwen3-Omni](/recipes-e2e-examples/qwen3-omni-asr) | Fine-tune for automatic speech recognition |

## Choose Where to Run

After choosing a tutorial, use [Run Jobs](/job-launchers/overview) for local workstations, Slurm, NeMo Run, SkyPilot, Kubernetes, and [Databricks](/recipes-e2e-examples/databricks).