MongoDB - Build AI That Scales
Mini toolsBGE Reranker v2 m3
BGE Reranker v2 m3 is the 568M lightweight reranker in the v2 family. The docs describe it as multilingual, easy to deploy, and fast at inference, while still offering strong reranking ability across languages. BAAI also explicitly recommends it as one of the preferred options for multilingual use cases and for efficiency-focused deployments.
Text
Gen 7
Overview
BGE Reranker v2 m3 is BAAI’s lightweight multilingual reranker in the v2 family. It is built for fast inference and easier deployment while keeping strong multilingual reranking capability, making it the efficiency-oriented option in the v2 lineup.
About Beijing Academy of Artificial Intelligence (BAAI)
Beijing Academy of Artificial Intelligence (BAAI), also known as Zhiyuan Institute, is a Chinese non-profit AI research laboratory established in November 2018. BAAI conducts fundamental AI research, develops open-source models (including WuDao, BGE embeddings, Emu, and RoboBrain), and fosters collaboration between academia and industry. Known for creating the BGE (BAAI General Embedding) series of embedding models used in RAG systems worldwide.
View Company ProfileTools using BGE Reranker v2 m3
No tools found for this model yet.
Last updated: April 16, 2026
