Simon Willison August 27, 2026 1 min signal 2026-08-27

Qwen3.8-Flash-Next

Archived text mirror, captured for personal reading when the Signal ran. Formatting is approximate — read the original at the source.

Simon Willison’s Weblog

Sponsored by: Teleport — AI agents don’t sleep and will try anything to achieve their goal. Teleport explains how to deploy AI safely, starting with an isolated ephemeral trusted runtime.

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

Simon Willison’s Weblog

Recent articles