Search and RAG

BGE (BAAI General Embedding)

Some of the most popular embeddings for search and RAG. The main v1.5 versions target English and Chinese; for Russian, BAAI has a separate model, bge-m3.

Developer
BAAI (Beijing Academy of Artificial Intelligence), China
First release
Aug 2023
Latest release
Sep 2025
Sizes
24M – 9B
License
Commercial use allowedMIT (v1, v1.5); Apache 2.0 (bge-en-icl, bge-code, bge-reasoner); bge-multilingual-gemma2 — under the Gemma license
Russian
Not supported
Ready-made builds
GGUF
Running
Available in OllamaAlso runs without a GPU
Industries
Software development, Customer support, Documents and accounting
Deploy on your server Hugging Face GitHub

What it does

  • Search across English-language documents
  • Picking passages for chatbot answers (RAG)
  • Code search (bge-code)

Where it is used

IT and software developmentInternal knowledge basesCustomer 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
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. bge-reasoner-embed
  2. bge-code-v1
  3. bge-en-icl и bge-multilingual-gemma2
  4. BGE v1.5 small, base, large
  5. BGE v1 (en, zh)

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 (BAAI General Embedding) be used in a commercial project?

Yes. License: MIT (v1, v1.5); Apache 2.0 (bge-en-icl, bge-code, bge-reasoner); bge-multilingual-gemma2 — under the Gemma license. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does BGE (BAAI General Embedding) 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 (BAAI General Embedding) support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download BGE (BAAI General Embedding) and what does it cost?

The BGE (BAAI General Embedding) 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.

Similar models

Search and RAGBGE-M3BAAI · ChinaCommercial use allowed

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.

DetailsSearch and RAGE5 / multilingual-e5Microsoft · USACommercial use allowed

Proven models for semantic search. The multilingual versions work well with Russian and are still a reliable base for RAG.

DetailsSearch and RAGGTEAlibaba · ChinaCommercial use allowed

Alibaba embeddings and rerankers for search: from tiny to 7B based on Qwen2. There is a multilingual mGTE version with long context.

Details

Source: huggingface.co/BAAI/bge-reasoner-embed-qwen3-8b-0923. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.