M5 Ultra Mac Studio Review: The Dream Mac for Local AI Agents
What happened
Federico Viticci 试了顶配 256GB 内存的 M5 Ultra Mac Studio，结论是它让本地跑的 AI 个人助手真正可用了。跟 M3 Ultra 和一台 RTX 5090 台式机比，M5 Ultra 赢在体积、发热和噪音上；5090 的内存带宽还是更高。他现在把 Qwen3.8-Flash-Next 模型设成了自己常用助手 A...
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pagePickM5 Ultra Mac Studio Review: The Dream Mac for Local AI Agents
Federico Viticci tested the 256GB M5 Ultra Mac Studio for local AI agents and found it makes locally-run personal assistants genuinely usable. Compared to an M3 Ultra and an RTX 5090 desktop, the M5 Ultra wins on size, thermals, and noise; the 5090 still leads in memory bandwidth. He now defaults to the Qwen3.8-Flash-Next model inside Open Minis and Hermes Agent, noting faster response starts, sustained speed at large context windows, and smooth multi-turn loops. He also uses local models as sub-agents orchestrated by GPT-6 Astra in Codex. The post does not disclose specific tokens-per-second or latency figures.