android-keyboard

e once you factor in power efficiency. The high end Android flagships running the Snapdragons elites (especially post Oryon acquisition) have no problems matching if not exceeding Apple hardware performance in terms of raw power but they are much more power hungry. At the end of the day, the current gen of "pocket scale" LLMs are still far from being able to be deployed at scale on mobile. Maybe in another year or two once RAM prices have fallen enough and mobile manufacturers build a lot more matmul and memory circuits into their SoCs instead of a tiny mostly useless "NPU/tensor processor" that doesn't have enough RAM to run anything useful. Current gen production mobile ML still heavily rely on traditional transfer learning like Apple's Core.ML (tiny pre trained models, with perhaps the final layer inference head swapped out). If you want a good example of production mobile ML, take a look at FUTO keyboard's transformer model for their keystroke prediction/autocorrect which operates in near real-time. https://github.com/futo-org/android-keyboard/blob/7ebbf5c8b5... I would say right now 100M-300M params is about the maximum you can do if you want any reasonable level of performance on your "average" non flagship mobile. I would keep to sub 100M for power efficiency sake.

-feature-to-a-closed-so...). I've shipped hardware projects that would have taken me months of learning in a few days (https://www.stavros.io/posts/i-made-a-voice-note-taker/). How's that?