> 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.

# Multimodal Models

## Introduction

Multimodal models in this section combine understanding and generation capabilities across text and visual modalities. These model families may use custom training recipes, packed multimodal datasets, or task-specific model wrappers beyond the standard image-text-to-text fine-tuning path.

## Supported Models

This table combines recipe-backed checkpoints with documented model families. Dates show when the current checkpoint first appeared in a recipe, or when a documentation-only family page was added. See the [combined model support log](/model-coverage/release-log) for recipe-backed checkpoints of every model type.

| Date       | Model                                                           | Architectures                                                | Recipe                                                                                                         |
| :--------- | :-------------------------------------------------------------- | :----------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------- |
| 2026-06-08 | [BAGEL-7B-MoT](/model-coverage/multimodal/bytedance-seed/bagel) | `BagelForUnifiedMultimodal`, `BagelForConditionalGeneration` | [recipe](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/multimodal_finetune/bagel/bagel_sft.yaml) |