Comment by make3 3 hours ago NVidia has reasonable incentives to keep things open indefinitely, it wants people to use it's GPUs 3 comments make3 Reply noosphr 3 hours ago Issue is that llama.cpp is the best way to run models on hardware that isn't nvidias. alightsoul 3 hours ago Except when they have less than 16 gb of ram? swozey 2 hours ago It'd be really nice if I could use my egpu 4090 on my macbook pro..
noosphr 3 hours ago Issue is that llama.cpp is the best way to run models on hardware that isn't nvidias. alightsoul 3 hours ago Except when they have less than 16 gb of ram?
Issue is that llama.cpp is the best way to run models on hardware that isn't nvidias.
Except when they have less than 16 gb of ram?
It'd be really nice if I could use my egpu 4090 on my macbook pro..