问 HN：M5 MacBook Pro 买家们，花这么多钱就为了可能在本地运行 LLM，值得吗？
5 分•作者: tpurves•5 个月前
今年要升级日常使用的 Mac 的朋友们，你们会考虑选择 Max 芯片 + 高内存的配置吗？例如，希望（现在或不久的将来）能够在自己的主力机器上实用性地运行 agent/LLM？
还是说，基础款和 Max 规格的 MacBook Pro 之间几千美元的差价，还是花在其他任何更实用的选择上更好（比如不同的硬件、远程硬件、云 AI 订阅或积分）？或者，再等等看会不会有 M5 Studio，或者明年的 M6 在推理性能上会有什么提升？
我很心动，但即使一些新模型变得更轻薄、更高效，我也不确定摩尔定律和 M5 这一代是否已经成熟到值得我这么做？
大家是怎么选择的，为什么？
查看原文
To anyone upgrading their daily driver Mac this year, are you considering going to a Max + high memory config? eg. with the hope (now or in near future) of being able to do usefully run agents/LLMs locally on your main machine?<p>Or is the few extra thousand dollars difference between a base and max-spec MBP still just better spent on literally any other practical option (like different harware, remote hardware, cloud AI subscriptions or credits). Or wait to see if there will be an M5 Studio or what inferencing performance next year's M6 may bring?<p>I am tempted, but even with some new models getting skinnier and more efficient, I am not sure moore's law and the M5 generation is quite there yet to be worth the trouble?<p>What call's are ya'll making and why?