Qwen 3.8 27B Scores 52, Matching Top Models Locally

Scobleizer · x · 2026-08-18

Qwen 3.8 27B achieved a score of 52 on Artificial Analysis, a massive milestone. It is the first time a model that can be run locally on a laptop is basically on par with the best proprietary models. This marks the point where local open-weight models are capable enough for most everyday tasks.

Related event: Qwen3.8-27B Benchmarks Rival Top Closed Models, Runs on a Single GPU(9 posts)→

Original post →

More from Models

Models channel →