Georgi Gerganov Praises Qwen3.6-27B as a Very Capable Local Coding Model
English summary
Georgi Gerganov, creator of llama.cpp and lead at ggml-org, reports daily use of Qwen3.6-27B for coding tasks over the past month and a half. He runs the model locally on an M2 Ultra Mac and an RTX 5090 box, using a stripped-down pi agent harness with the -nc --offline flags and a short system prompt. He finds it helpful for small maintainer tasks and affirms the model's capability for real-world, local AI-assisted programming. The endorsement comes from a Hacker News comment on the article "Running local models is good now" by Boykis.
Chinese summary
llama.cpp 创建者、ggml-org 负责人 Georgi Gerganov 表示，在过去一个半月里几乎每天使用 Qwen3.6-27B 模型处理编码任务。他在 M2 Ultra Mac 和 RTX 5090 机器上本地运行该模型，并搭配一个精简版的 pi 代理工具（使用 -nc --offline 参数和短系统提示）。他认为该模型对小的维护性任务很有帮助，并证实其在现实世界的本地 AI 辅助编程中能力出色。这段评价来自 Hacker News 上对 Boykis 文章《现在运行本地模型很好》的评论。
Key points
Georgi Gerganov has been using Qwen3.6-27B almost daily for coding tasks on local hardware.
Georgi Gerganov 几乎每天都在本地硬件上使用 Qwen3.6-27B 处理编码任务。
He runs the model on an M2 Ultra and an RTX 5090 with a stripped-down pi agent harness.
他在 M2 Ultra 和 RTX 5090 上运行模型，并使用精简版的 pi 代理工具。
The model is described as a capable and helpful tool for mundane maintainer tasks, supporting real-world local AI-assisted programming.
他将模型描述为处理普通维护任务的能干帮手，支持现实世界的本地 AI 辅助编程。