Image + text

Kimi-VL

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

Developer
Moonshot AI, China
First release
Apr 2025
Latest release
Jun 2025
Sizes
16B-A3B
License
Commercial use allowedMIT
Russian
Not stated
Ready-made builds
GGUF, MLX (Apple)
Running
On your own serverNeeds a GPU
Industries
Documents and accounting, Science and research
Deploy on your server Hugging Face GitHub

What it does

  • Analysing long PDFs and presentations
  • Answering questions about video
  • Operating interfaces from screenshots

Where it is used

Document workflowAnalyticsCustomer support

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Kimi-VL-A3B-Thinking-2506
  2. Kimi-VL-A3B Instruct и Thinking

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 Kimi-VL be used in a commercial project?

Yes. License: MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Kimi-VL 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 Kimi-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 Kimi-VL and what does it cost?

The Kimi-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

TextKimiMoonshot AI · ChinaCommercial use with conditions

Very large Moonshot MoE models for agentic work. K3 (2.8 trillion parameters) was the largest open model at release, with up to 1M tokens of context and image understanding; K2.7-Code is built for programming.

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 + textKeye-VLKuaishou · ChinaCommercial use allowed

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

Details

Source: huggingface.co/moonshotai/Kimi-VL-A3B-Thinking-2506. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.