> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/embedding-models/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/automodel/_mcp/server.

# Embedding Models

## Docs

- [Embedding Models](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/embedding-models/overview.md): Overview of NeMo AutoModel embedding models, including bidirectional Llama and Ministral3 backbones, Hugging Face AutoModel fallback, and bi-encoder recipes.
- [Meta](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/embedding-models/meta.md): Browse NeMo AutoModel coverage for models published by Meta for embedding workflows.
- [Llama-3.2-1B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/embedding-models/meta/Llama-3.2-1B.md): Use NeMo AutoModel to fine-tune Llama-3.2-1B for Embedding workflows with checked-in feature extraction recipes and documented distributed settings.
- [Mistral AI](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/embedding-models/mistralai.md): Browse NeMo AutoModel coverage for Mistral AI embedding models.
- [Ministral-3-3B-Base-2512](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/embedding-models/mistralai/Ministral-3-3B-Base-2512.md): Reference Ministral-3-3B-Base-2512 checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.
- [NVIDIA](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/embedding-models/nvidia.md): Browse NeMo AutoModel coverage for NVIDIA embedding models.
- [llama-embed-nemotron-8b](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/embedding-models/nvidia/llama-embed-nemotron-8b.md): Use llama-embed-nemotron-8b with NeMo AutoModel for embedding training, with documented checkpoints, runnable recipes, setup guidance, and model reference details.
- [llama-nemotron-embed-vl-1b-v2](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/embedding-models/nvidia/llama-nemotron-embed-vl-1b-v2.md): Extract multimodal embeddings with llama-nemotron-embed-vl-1b-v2 in NeMo AutoModel using the checked-in bi-encoder recipe and DDP.