Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things
- ID
- 14698
- Status
- summarized
- Published
- 17 Aug 2026, 6:00 AM
- Fetched
- 17 Aug 2026, 6:19 AM
- Provider
- Simon Willison
- Category
- developer-ai
- Original URL
- https://simonwillison.net/2026/Aug/16/qwen-38-27b/
- Source URL
- https://simonwillison.net/atom/everything/
Summary
- Score
- 7.5
- Created
- 17 Aug 2026, 6:20 AM
- Tags
- Audience
- developersvibe_codersai_ml_learners
What happened
Qwen 3.8 27B is a new Apache 2 licensed 27B vision-capable LLM from Alibaba with strong self-reported benchmarks, but it defaults to 'xhigh' reasoning effort, causing extreme overthinking on consumer hardware. A simple pelican SVG prompt took 21 minutes and 22,276 reasoning tokens to produce 3,223 output tokens; with reasoning disabled, the same prompt took 137s. The model also quickly exhausts LM Studio's default 8,192-token context limit during reasoning, requiring a manual increase to the full 262,144 maximum.
Why it matters
If you run Qwen 3.8 27B locally via LM Studio, immediately set reasoning_effort to 'medium' or 'low' and raise the context window above the 8,192 default—otherwise the model burns through your context budget on thinking and takes absurdly long for trivial tasks. The quality at xhigh is impressive (best local pelican SVG Simon Willison has seen), but the time cost is impractical for interactive use.
Discussion angle
The tradeoff between reasoning depth and latency on local models—when is xhigh worth the wait, and how should tooling handle reasoning_effort defaults so users don't hit context exhaustion on first run?