Model · BAAI · Reranking
BGE Reranker v2
BAAI's open reranker. Apache 2.0 weights, multiple sizes, and the open-weights default for self-hosted RAG pipelines that need a second-pass.
- Modality
- Reranking
- License
- Apache 2.0 (Open)
- Released
- March 1, 2024
- Last verified
- September 8, 2026
- Runs locally
- Yes
What you need to run it
- Mac
- Yes. Any Apple Silicon Mac (M1 or newer) with at least 8 GB (16 GB recommended) of memory. Newer chips are faster, but memory is what decides whether it runs.
- Windows / Linux PC
- NVIDIA works best. A graphics card with at least 4 GB (8 GB recommended) of video memory.
- No graphics card
- Works. Runs on a normal computer's processor, just slower.
Small enough for a laptop CPU, and community GGUF builds run in llama.cpp on a Mac.
Numbers are for: bge-reranker-v2-m3 (568M), 16-bit; GGUF builds also exist. Our estimate from the model’s size — the maker publishes no figure.
Strengths
- Apache 2.0 license
- Multiple sizes (m3, gemma, minicpm-layerwise) for different latency budgets
- Multilingual
Weaknesses
- Heavier than commercial rerankers at equivalent quality
- Reranking is always a second-pass tool
Try it
| Where | Type | Notes |
|---|---|---|
| Hugging Face | weights | Apache 2.0 |
| FlagEmbedding | local | Reference implementation |
Official sources
- Model card model
Change log
- — Added hardware requirements (Mac support, memory, NVIDIA). Source: estimate from size and community builds (HF BAAI/bge-reranker-v2-m3).
- — Verified current. No bge-reranker-v3 exists. The newer v2.5-gemma2-lightweight is a heavier variant under the restrictive Gemma licence, not a general replacement.
- — Initial entry.
Esc