Rerankers

Cross-Encoder MS MARCO (MiniLM, TinyBERT, mMARCO)

The most downloaded open rerankers: a tiny model reads a question-passage pair and scores how well they match. The multilingual mMARCO version covers Russian.

The last open version came out in Jun 2022. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
UKP Lab and the Sentence Transformers community, Germany
First release
Mar 2022
Latest release
Jun 2022
Sizes
about 4M – 120M
License
Commercial use allowedApache 2.0
Russian
Supported
Running
On your own serverAlso runs without a GPU
Industries
Customer support, Documents and accounting, Retail and marketplaces, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Reordering knowledge base search results
  • Selecting passages before a chatbot answers
  • Finding duplicates among tickets and product cards

Where it is used

Customer supportDocument managementE-commerce

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. mmarco-mMiniLMv2-L12 (14 языков, в том числе русский)
  2. ms-marco TinyBERT-L2, MiniLM-L2/L4/L6/L12, electra-base

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.

Frequently asked questions

Can Cross-Encoder MS MARCO (MiniLM, TinyBERT, mMARCO) be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Cross-Encoder MS MARCO (MiniLM, TinyBERT, mMARCO) 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 Cross-Encoder MS MARCO (MiniLM, TinyBERT, mMARCO) support Russian?

Yes, Russian is listed on the model card.

Where can I download Cross-Encoder MS MARCO (MiniLM, TinyBERT, mMARCO) and what does it cost?

The Cross-Encoder MS MARCO (MiniLM, TinyBERT, mMARCO) 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

RerankersBGE RerankerBAAI (Beijing Academy of Artificial Intelligence) · ChinaCommercial use allowed

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.

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.

DetailsRerankersColBERT (поиск с поздним взаимодействием)Stanford NLP, later Answer.AI and LightOn · USA and FranceCommercial use with conditions

A different search principle: every word of the question is compared with every word of the document, not the two texts as a whole. The index is heavier than with ordinary embeddings. The model cards list English.

Details

Source: huggingface.co/cross-encoder/mmarco-mMiniLMv2-L12-H384-v1. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.