Posts

just me that’s more excited about local #ai models?

google just posted about gemma 3n a nano model which they claim runs on 2GB of RAM (although god knows what gpu they used)

offline, fast(?), no limits, privacy friendly

seems cool – i am already impressed by running deepseek on my iphone atm

@gnukeith same here! i wish gemma would work on phones already :/ (seems like you can only use it on google ai studio for now)

can’t believe twitter is still half-down, this is insane

and elon wants this to be the sole way for the us gov to share info..?

I still find it pretty cool that the “comments” to the posts on my site are just replies to the posts on my other socials (twitter can’t do this bc of the price of @API)