Image + text

InternVL

A large family of Chinese vision models sized from 1B to 241B. InternVL-U (4B) combines image understanding, generation and editing.

Developer
Shanghai AI Laboratory (OpenGVLab), China
First release
Dec 2023
Latest release
Mar 2026
Sizes
1B – 241B-A28B
License
Commercial use allowedInternVL3.5: Apache 2.0; InternVL-U: MIT; some large versions inherit the base model's license (for example, Qwen)
Russian
Not stated
Ready-made builds
GGUF, AWQ
Running
On your own serverAlso runs without a GPU
Industries
Documents and accounting, Science and research, Manufacturing and logistics
Deploy on your server Hugging Face GitHub

What it does

  • Understanding documents, diagrams and charts
  • Answering questions about photos
  • Video analysis
  • Generating and editing images (InternVL-U)

Where it is used

Document workflowManufacturing and quality controlE-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
fits
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. InternVL-U
  2. InternVL3.5
  3. InternVL3
  4. InternVL2.5
  5. InternVL2
  6. InternVL 1.5
  7. InternVL

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 InternVL be used in a commercial project?

Yes. License: InternVL3.5: Apache 2.0; InternVL-U: MIT; some large versions inherit the base model's license (for example, Qwen). It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does InternVL 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 InternVL 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 InternVL and what does it cost?

The InternVL 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.

Comparisons

Similar models

Image + 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.

DetailsTextInternLM / Intern-SShanghai AI Laboratory · ChinaCommercial use allowed

Models from Shanghai AI Laboratory. The early InternLM line is general-purpose; the new Intern-S1/S2 is scientific: it understands formulas, molecules, charts and images.

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.

Details

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