# 阿里发布Qwen3.8-27B开源权重

- 来源：🚨 AI News | TestingCatalog (@testingcatalog)
- 发布时间：2026-08-14 23:07
- AIHOT 分数：51
- AIHOT 链接：https://aihot.virxact.com/items/cmst3jed003plro06fcgkjre5
- 原文链接：https://x.com/testingcatalog/status/2088281465549140264

## AI 摘要

阿里巴巴在Hugging Face以Apache 2.0协议发布Qwen3.8-27B权重，该原生多模态稠密模型仅27B参数，整体性能超越Qwen3.7-Plus，在真实编码与办公场景表现突出。模型支持262K原生上下文，可通过YaRN扩展至1M tokens，基准测试表现与Opus 4.6相当。Qwen3.8-2.4T-A95B（Max级）权重也已同步开放。

## 正文

Alibaba published Qwen3.8-27B weights on Huggingface under the Apache 2.0 license!

Qwen3.8-27B is a native multimodal dense model that you can run locally.
262K native context, extendable to 1M tokens via YaRN.
As a 27B model, it performs on par with Opus 4.6 on benchmarks!

Local testing time 👀

### 引用推文

> Qwen：We promised open weights for Qwen3.8. Now, time to meet them! 🎉 ⚡ Qwen3.8-27B: - A native multimodal dense model. With just 27B parameters, it outperforms Qwen...