Image + text

Keye-VL

Vision models from Kuaishou focused on short videos. Keye-VL-2.0 (30B, 3B active) understands well what happens in a clip and when.

Developer
Kuaishou, China
First release
Jun 2025
Latest release
May 2026
Sizes
8B – 671B-A37B
License
Commercial use allowedApache 2.0
Russian
Not supported
Ready-made builds
GGUF
Running
On your own serverNeeds a GPU
Industries
Media and production, Marketing and content
Deploy on your server Hugging Face GitHub

What it does

  • Analysing and describing short videos
  • Reviewing clips and content
  • Finding the right moment in a video
  • Answering questions about photos

Where it is used

Media and social networksMarketingContent moderation

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. Keye-VL-2.0-30B-A3B
  2. Keye-VL-671B-A37B
  3. Keye-VL-1.5-8B
  4. Keye-VL-8B-Preview

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 Keye-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 Keye-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 Keye-VL support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download Keye-VL and what does it cost?

The Keye-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

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.

DetailsImage + textKimi-VLMoonshot AI · ChinaCommercial use allowed

An efficient MoE vision model (16B, 3B active) with a long context and a reasoning version. Handles long documents and video well.

DetailsImage + textInternVLShanghai AI Laboratory (OpenGVLab) · ChinaCommercial use allowed

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

Details

Source: huggingface.co/Kwai-Keye/Keye-VL-2.0-30B-A3B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.