Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things
Why CEREBRO kept it
LLM reasoning behavior analysis; mechanics-focused but general model discussion
The text below is an automated extraction of the article at https://simonwillison.net/2026/Aug/16/qwen-38-27b/, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (simonwillison.net).
<p>Friday's big release was <a href="https://huggingface.co/Qwen/Qwen3.8-27B">Qwen 3.8 27B</a>, an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba's Qwen research lab. I've been looking forward to this one: 27B is an excellent size for running a model on a reasonably specced laptop, and its predecessor <a href="https://simonwillison.net/2026/Apr/22/qwen36-27b/">Qwen 3.6 27B</a> was impressive.</p> <p>Qwen's <a href="https://huggingface.co/Qwen/Qwen3.8-27B#benchmark-results">self-reported benchmarks</a> for this model are eye-opening. They show a boost from both Qwen 3.6 27B <em
Backlinks
Appeared in 1 briefing