undefined | Better HN

0 pointsModernMech8d ago0 comments

My hope is that we can get to the point I can run good-enough models on local hardware before they are all ad laden.

0 comments

You can already do this. Get an M5 Max with 129GB model and run a Qwen model. Or with for an M5 Ultra with 512GB of RAM and run Deepseek/Kimi/larger Qwen.

j / k navigate · click thread line to collapse

0 pointsModernMech8d ago0 comments

My hope is that we can get to the point I can run good-enough models on local hardware before they are all ad laden.

0 comments

aurareturn5d ago

You can already do this. Get an M5 Max with 129GB model and run a Qwen model. Or with for an M5 Ultra with 512GB of RAM and run Deepseek/Kimi/larger Qwen.

j / k navigate · click thread line to collapse