> 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/reranking-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.

# Reranking Models

## Docs

- [Reranking Models](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/reranking-models/overview.md): Reranking model coverage in NeMo AutoModel, including optimized Llama and Qwen3 backbones, Hugging Face Auto fallback, and supported workflows.
- [NVIDIA](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/reranking-models/nvidia.md): Browse NeMo AutoModel coverage for NVIDIA reranking models.
- [llama-nemotron-rerank-1b-v2](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/reranking-models/nvidia/llama-nemotron-rerank-1b-v2.md): Reference llama-nemotron-rerank-1b-v2 checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.
- [Qwen](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/reranking-models/qwen.md): Browse NeMo AutoModel coverage for Qwen reranking models.
- [Qwen3-Reranker-4B](https://docs.nvidia.com/nemo/automodel/nightly/model-coverage/reranking-models/qwen/Qwen3-Reranker-4B.md): Train Qwen3-Reranker-4B with NeMo AutoModel using context-aware query-document scoring, compatible checkpoint loading, and the retrieval training recipe.