Comment by ahartmetz
15 hours ago
It took me about three hours total to set up a local model. I already have a GPU and I have fiber for the download. llama.cpp is not difficult to compile and has many backends. It can run parts of the model on different backends, like in the common case that the GPU doesn't have enough VRAM for everything. There are many step-by-step guides available.
Takes even less depending on your system. LM Studio or Lemonade and you are set up in minutes and now they can even tell you what models will fit with the memory you have.
And it would be in seconds if models weren’t that large and slow-ish to download! LM studio is such a noob friendly experience, pretty neat first experience!
Three hours is a lot longer than one minute.