Qwen 3.8 27B: Open Weights, Best Local Dense Model Yet
Qwen 3.8 27B is out: open weights, best local dense model yet
Qwen releases Qwen3.8-27B, a 27B-parameter dense model with open weights, claiming it's the most capable open model yet. It excels in coding, agentic tasks, and multimodal understanding, with native vision-language support and flexible thinking control. The FP8 version offers near-identical performance and is compatible with major frameworks. Benchmarks show it outperforming larger models like Qwen3.7-Plus and Muse Glimmer-30B in many tasks.
Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability.