Skip to content
Hacker News front page

Running Local LLMs Offline on a Ten-Hour Flight

Dmitri Lerko ran Gemma 4 31B and Qwen 4.6 36B locally during a 10-hour flight with no Wi‑Fi. The MacBook Pro M5 Max had 128GB unified memory and a 40-core GPU; sustained load used about 1% battery per minute, and performance degraded past 100k tokens. The sharp finding is instrumentation: an iPhone cable delivered 60W, while a MacBook cable delivered 94W under the same load.

Why it matters: The author ran two local models offline on a maxed-out MacBook Pro M5 Max during a ten-hour flight, and logged how 60W versus 94W charging changed inference.

Read the original ↗Export Markdown