Code

Qwen Coder

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.

Developer
Alibaba (Qwen team), China
First release
Apr 2024
Latest release
Feb 2026
Sizes
0.5B – 480B-A35B
License
Commercial use allowedApache 2.0 (CodeQwen1.5 and Qwen2.5-Coder-3B have their own Qwen license)
Russian
Not stated
Ready-made builds
GGUF, AWQ, GPTQ, MLX (Apple)
Running
Available in OllamaAlso runs without a GPU
Industries
Software development
Deploy on your server Hugging Face GitHub

What it does

  • Code autocompletion in the editor
  • An agent that edits code in the repository on its own
  • Writing and refining scripts, SQL and integrations
  • In-house code review without data leaving the company

Where it is used

IT departmentsProduct developmentData analytics

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. Qwen3-Coder-Next 80B-A3B
  2. Qwen3-Coder 480B-A35B и 30B-A3B
  3. Qwen2.5-Coder 0.5B – 32B
  4. Qwen2.5-Coder 1.5B / 7B
  5. CodeQwen1.5-7B

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
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 Qwen Coder be used in a commercial project?

Yes. License: Apache 2.0 (CodeQwen1.5 and Qwen2.5-Coder-3B have their own Qwen license). It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Qwen Coder 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 Qwen Coder 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 Qwen Coder and what does it cost?

The Qwen Coder 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

TextQwenAlibaba · ChinaCommercial use with conditions

A family of language models with strong Russian language support, from small versions for a laptop to a flagship on par with commercial APIs.

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.

DetailsCodeDeepSeek-CoderDeepSeek · ChinaCommercial use with conditions

DeepSeek's coding model family: from small autocompletion models to the large MoE V2, which matched closed models in 2024. Later, coding moved into DeepSeek's general models.

Details

Source: huggingface.co/Qwen/Qwen3-Coder-Next. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.