News for hackers. Stuff that matters.

A comment on Qwen3.8-27B on the iPhone 18 Neural Engine at 15–70 tok/s (1.5 bpw).

Re:Qwen3.8-27B on the iPhone 18 Neural Engine at 15–70 tok/s... by spacecoder2 on Saturday October 17, 2026 @02:22PM (#50133631)
Anyone know how hot an iPhone gets running the Neural Engine flat out for 10 minutes?
[ Parent | on HN ]
Re:Qwen3.8-27B on the iPhone 18 Neural Engine at 15–70 tok/s... by GeekyBear on Saturday October 17, 2026 @03:03PM (#50134013)
The neural engine is optimized for energy efficiency, and the GPU is optimized for performance.

You're going to get much better battery life and much less heat running on the neural engine.

[ Parent | on HN ]
Re:Qwen3.8-27B on the iPhone 18 Neural Engine at 15–70 tok/s... by anemll on Saturday October 17, 2026 @02:24PM (#50133649)
It's warm but not hot. On M6 it's about 50% less energy consumption in my tests vs GPU. I think iPhone should be similar
[ Parent | on HN ]