Multimodal model

Qwen3.8-27B

Qwen3.8-27B is a 27B-parameter dense vision-language model from the Qwen3.8 series, built on the Qwen3.5 architecture. It understands text, images, and videos, with a flexible thinking mode that can be toggled and tuned for reasoning depth. It targets coding, professional work, research, and long-horizon agentic tasks, with a native context length of 262,144 tokens extensible to 1,000,000 tokens.

Type
Multimodal
Weights
Open
Downloads
6.7M
Likes
16k
Pipeline
image text to text
License
apache-2.0

Model hub

Qwen/Qwen3.8-27B

Repo
Qwen/Qwen3.8-27B
Library
transformers
Access
Public
Technical tags and languages
transformers safetensors qwen3_5 image-text-to-text conversational eval-results endpoints_compatible
Open on Hugging Face

Related tools

2

More from Alibaba

14

About Alibaba

1

Chinese e-commerce and cloud leader behind Taobao, Tmall, and Alipay.

Tools using Qwen3.8-27B

21