Developers wanting a mid-sized open model for front-end and repository-level coding can run it free under Apache 2.0.
Kenning's take
What it does
Qwen3.6-27B is the first open-weight model in Alibaba's Qwen3.6 series, released in April 2026. It is a 27-billion-parameter model with a vision encoder, aimed at agentic coding such as front-end work and repository-level reasoning, and adds an option to keep reasoning context across turns. It supports 262,144 tokens natively, extendable to about one million.
- 27B parameters with vision encoder
- Agentic coding improvements
- Thinking preservation across messages
- 262K context, extendable to about 1M
- Apache 2.0 open weights
Who it suits. Developers who want a mid-sized open model for coding agents on their own hardware.
Key facts
- Category
- AI models
- Part of
- Qwen
- Made by
- Alibaba (Qwen team)
- Based in
- China
- Released
- 21 April 2026
- How to get it
- Free download from Hugging Face; also in Qwen Chat
- Works on
- self-hosted, Hugging Face, Web
- In the UK
- Yes
- Free plan
- Yes, open weights
FAQ
When was Qwen3.6-27B released?
Its weights were published on Hugging Face on 21 April 2026.
Is Qwen3.6-27B open source?
Yes, under Apache 2.0.
What is Qwen3.6-27B good at?
Qwen highlights agentic coding, including front-end work and repository-level reasoning.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
MAI-UI
Alibaba Tongyi research models that operate smartphone apps by looking at the screen and tapping
Qwen-Image-2.0
Alibaba's 7-billion-parameter model that both creates and edits images, with strong text rendering at 2K
Qwen-Image-Layered
Open Alibaba model that splits an image into separate transparent layers so each part can be edited alone
Qwen-Image-3.0
Alibaba's hosted image model built for text-heavy layouts, taking prompts up to 4,500 tokens