MX
mxbai-embed-large
FeaturedA strong local embedding model for higher-quality semantic search and retrieval-augmented generation.
Embeddings#embeddings#semantic search#RAG#retrieval
mxbai-embed-large
mxbai-embed-large is a strong default when embedding quality matters and the machine can handle a slightly larger local embedding model.
Install Command
ollama run mxbai-embed-large
Best Fit
- Higher-quality semantic search.
- Knowledge base retrieval.
- Local RAG apps.
- Teams comparing embedding models before indexing large document sets.
Hardware Notes
Test retrieval quality with your real documents. A better embedding model helps, but chunking, metadata, and reranking can matter just as much.