Image + textComputer visionDocuments and OCR

WeVisOne-VL

A unified vision model from WeChat Vision (Tencent) based on Qwen3-VL: one model does both object search and precise perception. It finds objects by description, points to the needed item, counts items, marks points, reads text, and at the pixel level cuts out an object by description and makes an alpha matte on request, for which a small 9.6M-parameter decoder was added to the model. Two sizes, 2B and 4B. It suits image labeling, cutting products out of a background and counting items in a photo. Prompt languages are not stated on the card.

Developer
WeChat Vision, Tencent, China
First release
Oct 2026
Latest release
Oct 2026
Sizes
2B and 4B
License
Commercial use allowedApache 2.0
Russian
Not stated
Running
On your own serverNeeds a GPU
Industries
Retail and marketplaces, Media and production, Manufacturing and logistics
Deploy on your server Hugging Face GitHub

What it does

  • cutting items out of photos by description and an alpha matte for product cards
  • counting and finding items in photographs
  • labeling images for training other models

Where it is used

online stores and marketplacesmanufacturing and quality controlmedia and design

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. WeVisOne-VL-4B
  2. WeVisOne-VL-2B

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 WeVisOne-VL 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 WeVisOne-VL 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 WeVisOne-VL 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 WeVisOne-VL and what does it cost?

The WeVisOne-VL 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

Computer visionSegment Anything (SAM)Meta · USACommercial use with conditions

Selects any object in photos and videos with a click or a box. The basis for background removal and object counting.

DetailsImage + textQwen-VLAlibaba (Qwen team) · ChinaCommercial use allowed

One of the strongest open vision models: reads documents, tables, charts and video, and works with user interfaces. Since Qwen3.5, vision is built directly into the main Qwen model.

DetailsImage + textMiniCPM-VOpenBMB (ModelBest and Tsinghua University) · ChinaCommercial use allowed

Compact vision models that run even on a phone or laptop. Good at reading text in photos and understanding video; version 4.6 is only 1.3B. The fresh 4.7 comes in two sizes, 1B and 35B-A3B, the first MoE model in the family. According to the authors, 35B-A3B runs on an iPhone 17 Pro Max at 13+ tokens per second with 3 GB of memory thanks to their way of loading experts. The figures come from the authors themselves.

Details

Source: huggingface.co/tencent/WeVisOne-VL-4B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.