RerankingCheck model cardOpen weights

BGE Reranker v2 M3

BAAI · BGE

Lightweight multilingual reranker commonly used to improve RAG result ordering after vector search.

Best for

RAG builders who need a practical reranker after Qdrant, Chroma, pgvector, or other vector search.

Adds latency after retrieval; benchmark quality and speed on your corpus.

Much easier to run locally than frontier LLMs; CPU may be acceptable for small workloads.

Commonly used in local RAG stacks as a reranking step after vector search.

Local runtimes: Sentence Transformers, Transformers

Platforms: Windows, macOS, Linux

HardwareCPU or small GPURuntimeSentence Transformers, TransformersContextCheck model cardUpdated2026