Qwen3.8 27B

Über dieses Modell

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.

Technische Daten

Fähigkeiten

Eingabe-Modalitäten

Ausgabe-Modalitäten

Reasoning

Hybrid Standard on

Knowledge horizon