Model family
BGE Models
BGE models cover embeddings, reranking, retrieval, semantic search, and vector database workflows for RAG builders.
Best for
Embedding
Use this family hub to compare BGE variants for embedding workflows, then open the detail page for deeper deployment notes.
Reranking
Use this family hub to compare BGE variants for reranking workflows, then open the detail page for deeper deployment notes.
RAG
Use this family hub to compare BGE variants for rag workflows, then open the detail page for deeper deployment notes.
Search
Use this family hub to compare BGE variants for search workflows, then open the detail page for deeper deployment notes.
Variants
BGE models grouped by workflow
Embedding and reranking
BGE Reranker v2 M3
BAAI · BGE
Best for: RAG builders who need a practical reranker after Qdrant, Chroma, pgvector, or other vector search.
Local: Commonly used in local RAG stacks as a reranking step after vector search.
bge-m3
BAAI · BGE
Best for: RAG teams that want one embedding model for multilingual search, long documents, and retrieval experiments beyond plain dense vectors.
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
bge-large-en-v1.5
BAAI · BGE
Best for: English retrieval stacks that want a stronger embedding baseline for search and RAG before moving to multilingual models.
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
bge-base-en-v1.5
BAAI · BGE
Best for: Teams building English search or RAG systems on modest GPUs without dropping to the smallest embedding tier.
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
bge-small-en-v1.5
BAAI · BGE
Best for: Lightweight English embedding pipelines where CPU or modest GPU serving matters more than chasing the largest model.
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
bge-large-zh-v1.5
BAAI · BGE
Best for: Chinese embedding and retrieval workflows
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
bge-reranker-large
BAAI · BGE
Best for: Teams that already retrieve a candidate set and want a stronger final ranking step before passing context to an LLM.
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
bge-reranker-base
BAAI · BGE
Best for: Builders who want a practical reranking step in RAG or search without adding a heavyweight cross-encoder to every request.
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
bge-embedding-gemma2
BAAI · BGE
Best for: Gemma-based embedding experiments
Local: Use the exact checkpoint and quantization that matches your hardware and latency target.
Compare
All BGE models in the directory
| Model | Type | Best for | Local runner notes | License | Detail |
|---|---|---|---|---|---|
| BGE Reranker v2 M3 | Reranking | RAG builders who need a practical reranker after Qdrant, Chroma, pgvector, or other vector search. | Commonly used in local RAG stacks as a reranking step after vector search. | Check model card | Open |
| bge-m3 | Embedding | RAG teams that want one embedding model for multilingual search, long documents, and retrieval experiments beyond plain dense vectors. | Use the exact checkpoint and quantization that matches your hardware and latency target. | MIT | Open |
| bge-large-en-v1.5 | Embedding | English retrieval stacks that want a stronger embedding baseline for search and RAG before moving to multilingual models. | Use the exact checkpoint and quantization that matches your hardware and latency target. | MIT | Open |
| bge-base-en-v1.5 | Embedding | Teams building English search or RAG systems on modest GPUs without dropping to the smallest embedding tier. | Use the exact checkpoint and quantization that matches your hardware and latency target. | MIT | Open |
| bge-small-en-v1.5 | Embedding | Lightweight English embedding pipelines where CPU or modest GPU serving matters more than chasing the largest model. | Use the exact checkpoint and quantization that matches your hardware and latency target. | MIT | Open |
| bge-large-zh-v1.5 | Embedding | Chinese embedding and retrieval workflows | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |
| bge-reranker-large | Reranking | Teams that already retrieve a candidate set and want a stronger final ranking step before passing context to an LLM. | Use the exact checkpoint and quantization that matches your hardware and latency target. | MIT | Open |
| bge-reranker-base | Reranking | Builders who want a practical reranking step in RAG or search without adding a heavyweight cross-encoder to every request. | Use the exact checkpoint and quantization that matches your hardware and latency target. | MIT | Open |
| bge-embedding-gemma2 | Embedding | Gemma-based embedding experiments | Use the exact checkpoint and quantization that matches your hardware and latency target. | Check exact model card | Open |