At least one link/benchmark I saw said the ANE can be 7x faster than GPU (Metal ... | Hacker News

Hacker News .hnnew | past | comments | ask | show | jobs | submit

ks2048 on May 3, 2025 | parent | context | favorite | on: Run LLMs on Apple Neural Engine (ANE)

At least one link/benchmark I saw said the ANE can be 7x faster than GPU (Metal / MPS),

https://discuss.pytorch.org/t/apple-neural-engine-ane-instea...

It seems intuitive that if they design hardware very specifically for these applications (beyond just fast matmuls on a GPU), they could squeeze out more performance.

astrange on May 3, 2025 [–]

Performance doesn't matter. Nothing is ever about performance.

It's about performance/power ratios.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact