Hacker News

Favorites Setup
Comment by justincormack | original | Benchmarking Pocket-Scale Inference
[−]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.