Rerankers

BGE Reranker

Rerankers: they take passages found by search and reorder them by how well they actually match the question. v2-m3 is multilingual and lightweight, often paired with bge-m3.

The last open version came out in Jul 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 (Beijing Academy of Artificial Intelligence), China
First release
Sep 2023
Latest release
Jul 2024
Sizes
278M – 9B
License
Commercial use allowedMIT (base, large); Apache 2.0 (v2-m3, v2-gemma, v2-minicpm); v2.5-gemma2 — under the Gemma license
Russian
Not stated
Ready-made builds
GGUF, GPTQ, MLX (Apple)
Running
On your own serverAlso runs without a GPU
Industries
Software development, Customer support, Documents and accounting, Legal
Deploy on your server Hugging Face GitHub

What it does

  • Refining search results before a chatbot answers
  • Sorting knowledge base search results
  • Selecting the most relevant clauses of contracts and policies

Where it is used

Customer supportLegal and document managementInternal knowledge bases

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-reranker-v2.5-gemma2-lightweight
  2. bge-reranker-v2-m3, v2-gemma, v2-minicpm-layerwise
  3. bge-reranker-base и large

How to run it

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 Reranker be used in a commercial project?

Yes. License: MIT (base, large); Apache 2.0 (v2-m3, v2-gemma, v2-minicpm); v2.5-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 Reranker 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 Reranker support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download BGE Reranker and what does it cost?

The BGE Reranker 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 RAGQwen3 Embedding / RerankerAlibaba (Qwen) · ChinaCommercial use allowed

Embeddings and rerankers based on Qwen3, among the best open ones for multilingual search, including Russian. VL versions search images, screenshots and video.

DetailsRerankersJina RerankerJina AI · GermanyCommercial use with conditions

Strong multilingual rerankers; m0 also ranks pages as images (scans, slides). The latest versions are open for non-commercial use only.

Details

Source: huggingface.co/BAAI/bge-reranker-v2.5-gemma2-lightweight. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.