Visual document searchRerankers

MonoQwen2-VL (LightOn)

A reranker for document pages as images: after a visual search it reorders the found pages by how well they answer the question. The card does not state the languages.

Developer
LightOn, France
First release
Oct 2024
Latest release
Oct 2024
Sizes
2B (based on Qwen2-VL)
License
Commercial use allowedApache 2.0
Russian
Not stated
Running
On your own serverNeeds a GPU
Industries
Documents and accounting, Legal, Finance, Software development
Deploy on your server Hugging Face

What it does

  • Refining search results over scans and PDFs
  • Selecting pages before an AI assistant answers
  • Sorting retrieved slides and reports

Where it is used

Document managementLegal and complianceFinance and reporting

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. MonoQwen2-VL-v0.1

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 MonoQwen2-VL (LightOn) 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 MonoQwen2-VL (LightOn) need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does MonoQwen2-VL (LightOn) 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 MonoQwen2-VL (LightOn) and what does it cost?

The MonoQwen2-VL (LightOn) 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

Visual document searchColPali / ColQwenIlluin Technology (ViDoRe team) · FranceCommercial use with conditions

Searches PDFs and scans as images: pages do not need to be OCR'd first, the model finds the right one for a question directly, including tables and charts. Trained on English.

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.

DetailsRerankersLlama Nemotron RerankNVIDIA · USACommercial use with conditions

A small 1B reranker from NVIDIA. The vl version also takes document pages as images, not just text. The card states multilingual support without listing the languages.

Details

Source: huggingface.co/lightonai/MonoQwen2-VL-v0.1. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.