Qwen3.8 27B

About this model

Qwen3.8 27B is a 27B-parameter dense vision-language model built on the Qwen3.5 gated-delta architecture with a vision encoder, supporting a native 262K context window extensible to 1M tokens. It operates in a default thinking mode that can be disabled per request, with adjustable reasoning depth via reasoning_effort (xhigh, medium, low) and preserved thinking context across turns. The model achieves 89.2 on GPQA Diamond, 90.3 on LiveCodeBench v6, 61.7 on SWE-bench Pro, and 84.3 on OSWorld-Verified, demonstrating strong coding, agentic, and multimodal capabilities including native image and video understanding. It is released under the Apache 2.0 license.

Technical specifications

Capabilities

Input modalities

Output modalities

Reasoning

Hybrid Default on

Knowledge horizon