Model Releases
We promised open weights for Qwen3.8. Now, time to meet them! π β‘ Qwen3.8-27B: - A native multimodal dense model. With just 27B parameters,β¦
We promised open weights for Qwen3.8. Now, time to meet them! π β‘ Qwen3.8-27B: - A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world
We promised open weights for Qwen3.8. Now, time to meet them! π β‘ Qwen3.8-27B: - A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world coding & office workflows. - 262K native context, easily extendable to 1M tokens via YaRN. - Built for builders. Highly efficient, high-quality, and licensed under Apache 2.0. π The open weights for Qwen3.8-2.4T-A95B (Max-level) have also been released recently. Whether you're shipping lightweight applications with Qwen3.8-27B locally or building agents with Qwen3.8-2.4T-A95B, they're yours now! Download, deploy, and build something we haven't imagined yet. ππ - Hugging FaceοΌ https://huggingface.co/collections/Qwen/qwen38 - ModelScopeοΌ https://www.modelscope.cn/collections/Qwen/Qwen38
Related
- π’Meet Qwen3.8-Max β our most capable model to date. Next week, the open weights of Qwen3.8-Max will be released, and Qwen3.8-27B is also goβ¦
- Live and ready to build. Thanks for having us! @OpenRouter. Open weights dropping soon.β‘οΈ
- Thanks for the thorough testing! With Qwen3.8-Max, everyone can observe the world in detail. π
- Less than 2 hours to say hiπ. It's almost time! See you soon: π https://huggingface.co/Qwen/Qwen3.8-27B
Source: Qwen (X) | 2026-08-14