Code

KAT-Coder / KAT-Dev

Kuaishou models for agentic development, trained to solve real tasks in repositories. KAT-Coder-V2.5-Dev (35B, 3B active) is the open version of their closed flagship.

Developer
Kwaipilot (Kuaishou), China
First release
Sep 2025
Latest release
Jul 2026
Sizes
32B – 72B, 35B-A3B
License
Commercial use allowedApache 2.0
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Software development
Deploy on your server Hugging Face

What it does

  • An agent that fixes tasks in the repository
  • Code generation and refactoring
  • Automating routine development tasks

Where it is used

IT departmentsProduct development

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
fits

Versions

  1. KAT-Coder-V2.5-Dev 35B-A3B
  2. KAT-Dev-72B-Exp
  3. KAT-Dev 32B

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 KAT-Coder / KAT-Dev 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 KAT-Coder / KAT-Dev 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 KAT-Coder / KAT-Dev support Russian?

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

Where can I download KAT-Coder / KAT-Dev and what does it cost?

The KAT-Coder / KAT-Dev 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

CodeQwen CoderAlibaba (Qwen team) · ChinaCommercial use allowed

The broadest open coding family: from 0.5B for autocompletion to 480B for agents. Qwen3-Coder-Next (80B, 3B active) works as a developer agent on a single GPU.

DetailsCodeDevstralMistral AI (with All Hands AI) · FranceCommercial use with conditions

Mistral models for agentic development: they read the repository, edit files and run commands on their own. The 24B version fits on a single GPU.

DetailsCodeIQuest-CoderIQuest Research · ChinaCommercial use with conditions

A family of coding models with standard and reasoning versions, including a Loop variant that runs through its layers a second time. Sizes from 7B to 40B.

Details

Source: huggingface.co/Kwaipilot/KAT-Coder-V2.5-Dev. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.