BGE-M3
Open Weights
BAAI
BAAI's open-source multilingual embedding model, notable for Multi-Functionality (dense, sparse, and multi-vector retrieval), Multi-Linguality (100+ languages), and Multi-Granularity (inputs up to 8,192 tokens). It is the strongest open option for multilingual search, matching commercial quality when self-hosted.
Strengths
- Strongest open-source multilingual embedding model
- Dense, sparse, and multi-vector retrieval in one model
- 100+ languages
- Inputs up to 8,192 tokens
- Open MIT weights - self-hostable at commercial quality
Caveats
- Self-hosting requires embedding infrastructure
- Slightly below the very top commercial models on MTEB
- Tuning across retrieval modes adds integration work
- Vendor
- BAAI
- Context Window
- 8,192 tokens
- License
- MIT
- Release Date
- 2024-01-30
- Modalities
- text
Capabilities
Vision
Audio
Video
Tool Use
Resources
Pricing
Open weights under MIT - free to download and self-host; runs on modest hardware for high-throughput embedding.