Startup PrismML shrinks a large AI model for use in Apple's iPhone: report (seekingalpha.com) 1 points by nittanymount 5d ago ↗ HN
[–] nittanymount 5d ago ↗ wow, compressed qwen3.6:27B model (54GB) into 4GB, maybe it is not a general model anymore ?https://seekingalpha.com/news/4612644-startup-prismml-shrink...
[–] nittanymount 5d ago ↗ like to know more details. guess could use this model on local desktop as well.
2 comments
[ 2.1 ms ] story [ 12.7 ms ] threadhttps://seekingalpha.com/news/4612644-startup-prismml-shrink...