Skip to main content

BGE-M3

sentence-similarity

View on GitHub Official site
Embedding Models MIT Easy setup 35,541,030 stars

Overview

Description

The big picture: BGE-M3 is a multilingual embedding model that makes search and retrieval dramatically more accurate across 100+ languages. Here's why it matters: It handles short queries and long documents equally well in a single model — no need to maintain separate systems for different search types. The bottom line: Teams using RAG or semantic search get better results with less complexity.

Technical scorecard

License

MIT

Commercial use

Yes

OpenAI-compatible API

No

REST API

No

Fine-tuning support

Yes

Quantization support

No

Docker available

No

GUI / no-code available

No

Telemetry

Unknown

Offline after setup

Yes

Data & Privacy

Does it send data online?

After setup, this listing is marked as usable offline. Confirm network behavior against the upstream project before regulated deployment.

Does it store history?

Not verified in this directory yet. Review the upstream docs for persistence, logs, and workspace storage.

License checks?

Commercial use is marked as allowed or likely allowed by the listed license.

Telemetry?

Unknown

Last verified: Jul 22, 2026. Maintainer verification should be treated as directory guidance, not legal advice.

Setup & Installation

Easy

A developer can usually get this running with standard docs.

# Start with the official project repository
# https://huggingface.co/BAAI/bge-m3

Hardware Requirements

Hardware tagsCPU, GPU (NVIDIA)
LanguagesNot specified

Works Well With