Hacker News

Favorites Setup
Comment by teo_zero | original | Benchmarking Pocket-Scale Inference
[−]teo_zero · 2026-08-30 Sun 14:29 UTC · link
Tangent question: what about NPU performance? I always read about CPU vs GPU, but nobody talks about NPUs; I don't even know if llama supports them.

Why do phones and laptops get equipped with NPUs if there's no use for them?

[−]justincormack · 2026-08-30 Sun 15:00 UTC · link
I dont think llama does. There has been some work. They were originally designed for image processing (remove background from calls) and many exist because Microsoft mandated them for "AI laptops". Often they don't have much memory bandwidth, and are limited in compute and they are all incompatible with each other.