I’ve had pretty good luck running llamafile on my laptop. The speeds aren’t super fast, and I can only use the models that are Mistral 7B and smaller, but the results are good enough for casual use and general R and Python code.

Edit: my laptop doesn’t have a dedicated GPU, and I don’t think llamafile has support for Intel GPUs yet. CPU inference is still pretty quick.

We get it, you come from a life of privilege, conspicuous consumption, and performative capitalism, you don’t need to keep repeating yourself

Not necessarily. For example north east could have 3 people, north west 4 people, south west 3 people, and south east 4 people.

North and south each have 7 people, east and west both have 7, but the 4 quarters aren’t equal.