Bge m3
Model Overview¶
BGE-M3 is distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.
Multi-Functionality: It can simultaneously perform the three common retrieval functionalities of embedding model: dense retrieval, multi-vector retrieval, and sparse retrieval. Multi-Linguality: It can support more than 100 working languages. Multi-Granularity: It is able to process inputs of different granularities, spanning from short sentences to long documents of up to 8192 tokens.
- Model Source: BAAI/bge-m3
- License: MIT License
QPC Configurations¶
| Batch Size | SEQUENCE LENGTH | CORES | SoCs | QPC URL | QPC Size | QPC Download | Onnx URL | Onnx Download | Generation Date |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 512 | 8 | 1 | https://dc00tk1pxen80.cloudfront.net/SDK1.20.4/BAAI/bge-m3/BAAI--bge-m3_qpc_8cores_1bs_512seqlen_1devices_sdk1_20_4.tar.gz | 1.1GB | Download | https://dc00tk1pxen80.cloudfront.net/SDK1.20.4/BAAI/bge-m3/BAAI--bge-m3_ONNX_sdk1_20_4.tar.gz | Download | 26-June-2026 |