Visual document searchSearch and RAG

EVIE

Finds the right pages in documents as pictures, without turning them into text: matches a query against how the page looks. Version 8B scores 66.75 on ViDoRe V3. The index can be compressed to 32 vectors per page.

Developer
Tencent, China
First release
Aug 2026
Latest release
Sep 2026
Sizes
4.5B и 8B
License
Commercial use allowedApache 2.0
Russian
Not stated
Ready-made builds
GGUF
Running
On your own serverNeeds a GPU
Industries
Documents and accounting, Legal, Finance, Retail and marketplaces
Deploy on your server Hugging Face GitHub

What it does

  • searching scans, slides and reports without text recognition
  • RAG over documents with tables and charts
  • searching archives of contracts and catalogs

Where it is used

document management and archiveslegal departmentsknowledge 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. EVIE-4.5B и EVIE-8B
  2. EVIE-Preview-4.5B

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 EVIE 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 EVIE need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller 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 EVIE 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 EVIE and what does it cost?

The EVIE 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

RerankersColBERT (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.

DetailsVisual document searchLlamaIndex vdrLlamaIndex · USACommercial use allowed

A small model for searching document pages as images, from the team behind a popular RAG framework. The card lists English, Italian, French, German and Spanish.

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.

Details

Source: huggingface.co/tencent/EVIE-4.5B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.