Wispr Flow - Don’t type, just speak
Mini toolsBGE Reranker v2 minicpm layerwise
BGE Reranker v2 minicpm layerwise is a 2.72B multilingual reranker designed for more controllable efficiency. The docs say it is suitable for multilingual contexts and allows users to select which layer to output from, which helps accelerate inference. BAAI also recommends it particularly for Chinese or English use cases when users want a balance between quality and controllable speed.
Text
Gen 7
Overview
BGE Reranker v2 minicpm layerwise is BAAI’s layer-selectable multilingual reranker in the v2 family. It is built to let users choose output layers for accelerated inference, trading some depth for speed while keeping strong multilingual reranking performance.
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 Profile
Last updated: April 16, 2026
