Alibaba's Qwen team launched Qwen3.6-27B, a new open-weight dense AI model featuring 27 billion parameters. The model uses the open-source Apache 2.0 license. It is available for download on platforms including Hugging Face and ModelScope.
The 27B dense model outperforms the much larger Qwen3.5-397B-A17B Mixture-of-Experts model across all major coding benchmarks. It achieved superior results on SWE-bench and Terminal-Bench without the complexity of MoE architecture.
This multimodal model processes text, image, and video inputs. Its smaller size aims to reduce costs for developers building AI-powered coding tools and agents.