05:16
2026-09-11
dev.to
large-language-models
Can Qwen 3.8 running on your laptop really replace Claude Opus for Agentic coding?
A developer reports that Qwen 3.8 27b, a locally run open-source model, now matches frontier cloud models like Claude Opus 4.6 for agentic coding tasks, scoring 34 versus 32 on the Artificial Analysis…