25d • 💬 Off-Topic & Networking
Run 397B model on 48GB RAM
First Google’s TurboQuant and then this repo: https://github.com/danveloper/flash-moe
Innovations like these will make local hosting more and more practical.
2
7 comments
Run 397B model on 48GB RAM
skool.com/shipping-skool
build and ship real software with AI, no coding needed. 8 live calls/week, starter kit, and a community that actually builds stuff
Leaderboard (30-day)
1
+119
2
+22
3
+19
4
+16
5
+15
Powered by