FactArticle

Qwen 3.8 27B has sufficient capability in long context, code generation, and tool-calling to successfully drive a coding agent loop on consumer hardware.

Local experimentation with the Pi coding agent showed promising results. The model analyzed a codebase and built a working utility tool to convert session transcripts to markdown. ✦ AI generated

Simon Willison · Simon Willison's Weblog · 2026-08-16 · original ↗

Share card ↓Export .md Export .txt

One of the biggest questions around local models is whether or not they have enough horsepower to successfully run a coding agent loop. Coding agents require long context, strong code generation support and reliable tool-calling. On paper Qwen 3.8 27B has all three of these, so is it up to the task? My initial experiments with Pi have been very promising.

Read full article ↗excerpt · fair-use quotation

✳ Pi ✳ Qwen 3.8 27B

Around this claim

Evidence · 1

Qwen 3.8 27B is highly accurate at generating bounding box coordinates for objects in photographs, producing near-perfect results on its first attempt.Simon Willison · Simon Willison's Weblog · conf 60%

This moment responds to

provides context → The ambition of what I even consider building has gone up a lot because of coding agents — you can push agents to end-to-end implement, verify, and maintain stuff, making you much more ambitious and your output more robust.Simon Last · No Priors supports → Qwen3.8-Max demonstrates autonomous long-horizon and multimodal capabilities including 10+ days of unattended coding, a 125-hour autonomous research loop that beat an original paper's benchmark by +2.71 points, silicon design from RTL to physical layout, and product-grade outputs across professional workflows.AINews · Latent Space