Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Generative AI Is Coming to Phones Soon.
The page says they shrunk it by quantizing from FP32 to INT8.
What I can't tell... is there a demo app? Can this be run today on a Qualcomm based device?
There are no comments on this comment yet.
The page says they shrunk it by quantizing from FP32 to INT8.
What I can't tell... is there a demo app? Can this be run today on a Qualcomm based device?