---
title: "Qwen3.8-Flash-Next"
type: signal
url: https://frontiernewswire.com/s/qwen3-8-flash-next-vc66ebdce
published: 2026-08-26T23:52:58.000Z
byline: "Source: Simon Willison"
---

# Qwen3.8-Flash-Next

Source: Simon Willison · Published 2026-08-26 · Canonical: https://frontiernewswire.com/s/qwen3-8-flash-next-vc66ebdce

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 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: Via Hacker News Tags: ai , generative-ai , llms , qwen , pelican-riding-a-bicycle , ai-in-china , nvidia-spark

In this story: [Qwen](https://frontiernewswire.com/models/qwen), [Nvidia DGX Spark](https://frontiernewswire.com/models/nvidia-dgx-spark), [Qwen 4](https://frontiernewswire.com/models/qwen-4), [Qwen3.8-Flash-Next](https://frontiernewswire.com/models/qwen3-8-flash-next)

## Sources

- [Read the original at Simon Willison](https://simonwillison.net/2026/Aug/26/qwen38-flash-next/)

## Related on Frontier

- [\[AINews\] LLMs can read \& write neural network weights: "Weight Space Programming" cuts Autoresearch out of the RSI loop](https://frontiernewswire.com/s/ainews-llms-can-read-write-neural-network-weights-weight-space-6e130d2f)

---

[More Latest Signal](https://frontiernewswire.com/) · [Signals](https://frontiernewswire.com/verified-reporting)