Alibaba's Qwen Releases Open 27B Vision Model
The new dense model, licensed under Apache 2.0, brings both text and image understanding to the midrange parameter space.
Alibaba's Qwen team continues to expand its open-source offerings with the release of Qwen3.6-27B, a powerful new multimodal model. This dense, 27-billion-parameter model is designed to understand and process both text and images, making it a versatile foundation for a wide range of AI applications.
The model's 27B size places it in an interesting position within the open-source landscape. It offers a significant step up in capacity from the common 7B and 13B models without requiring the substantial hardware resources needed to run models in the 70B+ class. This makes it a compelling option for developers seeking a balance between high performance and operational efficiency.
A Permissive and Capable Model
A key feature of this release is its Apache 2.0 license, which permits broad commercial use and modification. This permissive approach encourages adoption and integration into commercial products, distinguishing it from models with more restrictive licenses. The Qwen team has positioned the model as a strong generalist for various vision-language tasks.
Developers can access the model weights and usage instructions directly from the official Hugging Face repository. As another strong entry in the Qwen series, this release further solidifies the team's commitment to providing capable, openly accessible AI models.
Sources
More in Vision-Language

Thinking Machines Debuts Inkling Small, a Compact Multimodal MoE
The Apache-2.0 model brings mixture-of-experts efficiency to image, audio, and text tasks in a smaller footprint.

Microsoft's Mage-VL Streams Video Natively
A codec-native multimodal foundation model aims to understand live video and vision-language input in real time.
Apertus v1.5 70B arrives with an Apache-2.0 license
Switzerland's open-model effort ships a 70-billion-parameter, multilingual and multimodal system that anyone can use, modify, and deploy.
0 comments
No comments yet. Be the first to weigh in.