Search and RAG

BGE-M3

A model for meaning-based search in about a hundred languages. The core of RAG: the bot finds the right part of a document before answering.

The last open version came out in Jan 2024. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
BAAI, China
First release
Jan 2024
Latest release
Jan 2024
Sizes
568M
License
Commercial use allowedMIT
Russian
Supported
Ready-made builds
GGUF, MLX (Apple)
Running
Available in OllamaAlso runs without a GPU
Industries
Customer support, Documents and accounting, Legal
Deploy on your server Hugging Face GitHub

What it does

  • Search across a document base
  • RAG for a chatbot
  • Finding similar requests and duplicates

Where it is used

Knowledge basesLegal archivesCustomer support

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. BGE-M3

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can BGE-M3 be used in a commercial project?

Yes. License: MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does BGE-M3 need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does BGE-M3 support Russian?

Yes, Russian is listed on the model card.

Where can I download BGE-M3 and what does it cost?

The BGE-M3 weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Comparisons

Source: huggingface.co/BAAI/bge-m3. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.