Simon Willison's Weblog

Qwen3.8-Flash-Next

8.5内容质量
Qwen3.8-Flash-Next

TL;DR · AI 摘要

Qwen3.8-Flash-Next是通义千问推出的多模态MoE模型，具有125B参数和显著性能提升。

核心要点

  • Qwen3.8-Flash-Next采用多模态MoE架构，是Qwen4的早期预览版本
  • 模型总参数量达125B但仅6B活跃参数，性能提升显著
  • 在DGX Spark上使用Unsloth量化模型实现72.5GB/78.9GB版本测试

结构提纲

按章节快速跳转。

  1. §模型发布

    介绍Qwen3.8-Flash-Next作为Qwen4的预览版本

  2. ·技术架构

    阐述多模态MoE模型的创新设计和参数规模

  3. ›性能优化

    解释通过量化技术实现的性能提升机制

  4. ·测试实践

    描述在DGX Spark上的具体测试配置和结果

思维导图

用一张图看清主题之间的关系。

查看大纲文本（无障碍 / 无 JS 友好）
  • Qwen3.8-Flash-Next
    • 技术特性
      • 多模态MoE架构
      • 125B参数规模
    • 优化方案
      • 量化技术
      • 6B活跃参数
    • 测试环境
      • DGX Spark
      • Unsloth量化模型

金句 / Highlights

值得收藏与分享的关键句。

#AI#LLM#模型架构#量化技术
打开原文

Qwen3.8-Flash-Next

Simon Willison’s Weblog

Subscribe

#smallhead

Sponsored by:

Greptile — The Al code reviewer that runs your code. Catch bugs that only show up at runtime.

Try it for free

26th August 2026 - Link Blog

Qwen3.8-Flash-Next ( via ) Another open weights model from Qwen. This one is "a multimodal MoE model that also serves as an early preview of the architecture used in Qwen4".

It's pretty big: 125B tokens, but only 6B active which means it gets a significant performance boost.

I've been trying it out on a DGX Spark using these Unsloth quantized models . I'm still exploring the model - so far I've tried the 72.5GB UD-IQ1_S one (producing these pelicans ) and the 78.9GB UD-Q2_K_XL (producing these ).

My favorite so far was this xhigh reasoning effort one from UD-Q2_K_XL:

Posted

26th August 2026

at 11:52 pm

Recent articles

  • Conceptual integrity and counting lines of code - 19th August 2026
  • Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things - 16th August 2026
  • Now we have a timeline of the OpenAI accidental attack against Hugging Face - 7th August 2026

#primary

This is a link post by Simon Willison, posted on 26th August 2026 .

ai

2,206

generative-ai

1,955

llms

1,922

qwen

61

pelican-riding-a-bicycle

137

ai-in-china

108

nvidia-spark

6

Monthly briefing

Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.

Pay me to send you less!

Sponsor & subscribe

.metabox

#secondary

#wrapper

  • Disclosures
  • Colophon
  • ©
  • 2002
  • 2003
  • 2004
  • 2005
  • 2006
  • 2007
  • 2008
  • 2009
  • 2010
  • 2011
  • 2012
  • 2013
  • 2014
  • 2015
  • 2016
  • 2017
  • 2018
  • 2019
  • 2020
  • 2021
  • 2022
  • 2023
  • 2024
  • 2025
  • 2026