> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/automodel/v0.7/model-coverage/large-language-models/deepseek-ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/automodel/_mcp/server.

# DeepSeek AI

> Browse NeMo AutoModel coverage for DeepSeek AI large language models.

* [`deepseek-llm-7b-chat`](/model-coverage/large-language-models/deepseek-ai/deepseek-llm-7b-chat)
* [`DeepSeek-V3`](/model-coverage/large-language-models/deepseek-ai/DeepSeek-V3)
* [`DeepSeek-V3.2`](/model-coverage/large-language-models/deepseek-ai/DeepSeek-V3.2)
* [`DeepSeek-V4-Flash`](/model-coverage/large-language-models/deepseek-ai/DeepSeek-V4-Flash)
* [`DeepSeek-V4-Pro`](/model-coverage/large-language-models/deepseek-ai/DeepSeek-V4-Pro)
* [`DeepSeek-V4.1-Flash`](/model-coverage/large-language-models/deepseek-ai/DeepSeek-V4.1-Flash)

> Browse NeMo AutoModel coverage for DeepSeek AI large language models.

## Docs

- [deepseek-llm-7b-chat](https://docs.nvidia.com/nemo/automodel/v0.7/model-coverage/large-language-models/deepseek-ai/deepseek-llm-7b-chat.md): Reference deepseek-llm-7b-chat checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.
- [DeepSeek-V3](https://docs.nvidia.com/nemo/automodel/v0.7/model-coverage/large-language-models/deepseek-ai/DeepSeek-V3.md): Reference DeepSeek-V3 checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.
- [DeepSeek-V3.2](https://docs.nvidia.com/nemo/automodel/v0.7/model-coverage/large-language-models/deepseek-ai/DeepSeek-V3.2.md): Use NeMo AutoModel to fine-tune DeepSeek-V3.2 for LLM workflows with checked-in text generation recipes and documented distributed settings.
- [DeepSeek-V4-Flash](https://docs.nvidia.com/nemo/automodel/v0.7/model-coverage/large-language-models/deepseek-ai/DeepSeek-V4-Flash.md): Use DeepSeek-V4-Flash with NeMo AutoModel for language model fine-tuning, with documented checkpoints, runnable recipes, setup guidance, and model reference details.
- [DeepSeek-V4-Pro](https://docs.nvidia.com/nemo/automodel/v0.7/model-coverage/large-language-models/deepseek-ai/DeepSeek-V4-Pro.md): Fine-tune DeepSeek-V4-Pro with NeMo AutoModel using the checked-in multi-node recipe with pipeline and expert parallelism.
- [DeepSeek-V4.1-Flash](https://docs.nvidia.com/nemo/automodel/v0.7/model-coverage/large-language-models/deepseek-ai/DeepSeek-V4.1-Flash.md): Fine-tune DeepSeek-V4.1-Flash with NeMo AutoModel using checked-in expert-parallel text recipes and sharded Engram memory.