---
title: "Qwen发布Qwen3.8-Flash-Next：多模态MoE模型，预览Qwen4架构"
source: "Simon Willison 博客（Atom）"
source_tier: "t2"
url: "https://simonwillison.net/2026/Aug/26/qwen38-flash-next/"
permalink: "https://feed.astralor.com/items/itm_63366f5f9044fc451f21041b"
published: "2026-08-26T23:52:58.000Z"
score: 74
channel: "ai"
tags: ["MoE","Qwen","Qwen3.8-Flash-Next","开源模型"]
---

# Qwen发布Qwen3.8-Flash-Next：多模态MoE模型，预览Qwen4架构

## AI 点评

> 这不仅仅是新模型发布，而是首次有人把Qwen3.8-Flash-Next跑起来并告诉你哪个量化版本值得试。对于想跟进下一代架构的人来说，这篇博客比官方公告更有参考价值。

## 速览

Qwen推出开源多模态MoE模型Qwen3.8-Flash-Next，总参数125B但仅激活6B，性能显著提升，并作为Qwen4架构的早期预览。Simon Willison在DGX Spark上通过Unsloth量化版本进行了测试，尝试了72.5GB的UD-IQ1_S和78.9GB的UD-Q2_K_XL，并特别推荐了UD-Q2_K_XL的高推理强度配置。该模型延续Qwen开源路线，值得关注。

## 关键点

- Qwen3.8-Flash-Next是开源多模态MoE模型，总参数125B，激活参数仅6B。
- 该模型被视为Qwen4架构的早期预览，性能提升明显。
- Simon Willison在DGX Spark上使用Unsloth量化版本实测，推荐UD-Q2_K_XL高推理强度配置。

## 全文

Qwen3.8-Flash-Next 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 pretty big 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: Via Hacker News Tags: ai, generative-ai, llms, qwen, pelican-riding-a-bicycle, ai-in-china, nvidia-spark

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_63366f5f9044fc451f21041b