Alibaba releases Qwen3.8: 27B open-source model with 262K context
ProfBuehlerMIT · x · 2026-08-15
Alibaba has released the open weights for the Qwen3.8 series:
- Qwen3.8-27B: A native multimodal dense model with 27B parameters. It outperforms Qwen3.7-Plus overall and excels in real-world coding and office workflows. It features a native 262K context window, extendable to 1M tokens via YaRN, and is licensed under Apache 2.0.
- Qwen3.8-2.4T-A95B: Weights for the Max-level model are also available.
- Ecosystem Support: The mistralrs library now supports running Qwen3.8-27B, offering built-in local web search, code execution, and full OpenAI API compatibility across CPU, Mac, and CUDA.
Related event: Alibaba Open-Sources Native Multimodal Qwen3.8-27B Model(48 posts)→
More from Models
- 200 chess games suggest in-context learning doesn't work yet, experimenter says — akbirthko · 2026-10-16
- OpenAI's internal model shows real math "research taste," experts say its proofs go beyond prior literature — cong_ml · 2026-10-16
- User catches Opus spinning up throwaway zz- debug scripts, echoing the METR OAI-HuggingFace incident — holdenmatt · 2026-10-16
- OpenAI drops 722 math papers tied to unreleased model, mathematicians demand receipts — thursdai_pod · 2026-10-16
- Fable 5/5.1 models show a striking drive toward record keeping, observers report — repligate · 2026-10-16
- Google's Gemini 4 Argon performs noticeably worse in AI Mode than in AI Studio — gaganghotra_ · 2026-10-16