Qwen3.8-27B 在 Mac 上跑起来：内存、引擎与测试全流程
教你把 Qwen3.8-27B 装进 Mac 本地跑代码，内存要多少、怎么配引擎、测试怎么兜底都写清楚了，还能当 Claude Code 的免费备胎。
Qwen3.8-27B 以 17.6 GB 的文件形式可以装进消费级 Mac，但 MLX 引擎在开启 draft-ahead 后峰值内存达 23.6 GB，24 GB 内存只能勉强加载。文章给出具体门槛：32 GB 内存才适合跑智能体，48 GB 才能承载机器可校验的 /goal，16 GB 内存不适合这个模型。作者强调在 Claude Code 或 Codex 之外搭建本地私有回路的关键是三件事：内存达标的推理引擎、带停止条件的执行框架、自己维护的测试。本地 token 没有账单，runaway 不会产生费用，测试就是停止线。配套提供了包含拉取、安装、skill 文件和 git-config 检查的交互式 HTML 教程。
People keep lining Qwen3.8-27B up with Opus 4.6, the coding frontier from a few months ago.
So, can that class of model sit on a consumer Mac?
Yes, but you still need to build the stack around it: > an engine that quotes peak RAM > a harness with a stop > and tests you own
If you already use Claude Code or Codex, this is a private loop beside that bill.
Qwen3.8-27B fits a Mac as a 17.6 GB file. But MTPLX still peaks at 23.6 GB once the draft-ahead head is on.
A speed taken on a 128 GB Mac with thinking turned off is a different machine, so leave it out of a 24 GB average.
Two ways this goes wrong:
> You stop at the download, and 24 GB of RAM only loads it tight. A 4-bit copy there is still perfect for most tasks. 32 GB is the first real agent. 48 GB can hold a /goal that a machine can check. 16 GB is not this model.
> Or you stop at the first hour. Ollama is a fine look, but after that you still pick an engine, a harness, and a stop.
Local tokens have no invoice, so a runaway does not get expensive, and you still own the merge. Tests are the stop.
We put the pulls, the install, the skill files, and the git-config check on an interactive HTML tutorial.
Which file to pick if you already live in MLX, and what to refuse to train this week, are a longer argument.
Full breakdown below
