Model Releases

Qwen open-sources Qwen3.8 series models

Original title:We promised open weights for Qwen3.8. Now, time to meet them! 🎉 ⚡ Qwen3.8-27B: - A native multimod...

AI summary

Qwen has fulfilled its commitment by open-sourcing the Qwen3.8 series. Qwen3.8-27B is a native multimodal dense model that surpasses Qwen3.7-Plus across the board with only 27B parameters. It natively supports a 262K context, extendable to 1M tokens via YaRN, and is released under the Apache 2.0 license. The open weights of the Max-tier Qwen3.8-2.4T-A95B have also been released simultaneously.

Key Takeaways

  • Qwen has fulfilled its commitment by open-sourcing the Qwen3.
  • 8 series.
  • 8-27B is a native multimodal dense model that surpasses Qwen3.
  • 7-Plus across the board with only 27B parameters.
  • It natively supports a 262K context,extendable to 1M tokens via YaRN,and is released under the…

Quick Facts

Published
Updated
Source
X:通义千问 / Qwen (@Alibaba_Qwen)
Category
Model Releases
AI score
71
Read the original Read the full article at the original source
Why it matters

官方称 27B 稠密多模态模型整体表现超过 Qwen3.7-Plus,262K 原生上下文可扩至 1M,Apache 2.0 协议下本地部署轻量应用多了一个更高效的选择。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Qwen open-sources Qwen3.8 series models. August 14, 2026. https://new.nat6.net/en/news/cmst3j53e03ncro068tgsr4xn/

View all →