Skip to main content

Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things

Simon WillisonNotableConfirmed

Why Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things matters

Qwen 3.8 27B is a capable open-source vision model suitable for local deployment, but developers need to understand its reasoning_effort defaults and tune parameters for their use case—the xhigh default causes extreme over-thinking that makes it impractical for most tasks without adjustment.

Read the full article at Simon Willison

CoFabrix summarises and comments on this story. The original reporting belongs to Simon Willison.

More in Benchmark

Browse the full AI Pulse feed

Seeing AI Disruption in Your Industry?

Find out where your organization stands -- and what to do about it.