Qwen 3.8 27B review: excellent model defaults to hilarious overthinking
marlene_zw · x · 2026-08-17
Simon Willison published an in-depth review of Alibaba's Qwen 3.8 27B model. Licensed under Apache 2.0, this vision-capable LLM shows impressive benchmark improvements over its predecessor and the closed-weight Qwen 3.7-Plus. Running a quantized version on both a MacBook Pro and an NVIDIA DGX Spark, Willison discovered that the model defaults to maximum reasoning depth. This causes it to engage in spectacular overthinking even for mundane tasks, rapidly consuming context windows and resources. While entertaining, this default configuration is inefficient for practical use.
Related event: Qwen3.8-27B Local Tests Praise It for Approaching Claude Opus(6 posts)→
More from Models
- Dev: Claude writes 'zero bugs' on healthcare apps, 10x token efficiency — repligate · 2026-10-16
- Shanghai AI Lab unveils Intern Lumina U2, a diffusion LLM unifying image, video and 3D tasks — Shanghai-AI-Laboratory · 2026-10-16
- This Week in Tech breaks down Gemini 4, OpenAI's Dots agents, and Anthropic's leaked IPO filing — LouMM · 2026-10-16
- Sentry CEO Reveals $8,972 Claude Bill as Opus 'Scope Creeps' Through Team Workloads — zeeg · 2026-10-16
- Opus 5.5 wins: Anthropic reclaims token and spend share from OpenAI in 6 days — FinanceYF5 · 2026-10-16
- will.deeb: asking why a minor lab benchmarked against a 2-month-old frontier model is usually a stupid question — willcb · 2026-10-16