Comment by apitman 2 days ago I wonder how this would stack up against 4x RTX 3060, assuming you have the physical room for them. 3 comments apitman Reply Almondsetat 2 days ago Since the 3060s would have to communicate constantly using pcie, I think I'd go with intel apitman 2 days ago Currently software is king when it comes to inference performance though. Almondsetat 2 days ago Having the entire model in the vram without having to transfer anything is even more king, though
Almondsetat 2 days ago Since the 3060s would have to communicate constantly using pcie, I think I'd go with intel apitman 2 days ago Currently software is king when it comes to inference performance though. Almondsetat 2 days ago Having the entire model in the vram without having to transfer anything is even more king, though
apitman 2 days ago Currently software is king when it comes to inference performance though. Almondsetat 2 days ago Having the entire model in the vram without having to transfer anything is even more king, though
Almondsetat 2 days ago Having the entire model in the vram without having to transfer anything is even more king, though
Since the 3060s would have to communicate constantly using pcie, I think I'd go with intel
Currently software is king when it comes to inference performance though.
Having the entire model in the vram without having to transfer anything is even more king, though