[fullstackwife]

I hope for proliferation of 100% local coding assistants, but for now the recommendation of "Works best on $10K+ GPU" is a show stopper, and we are forced to use the "big company". :(

[danw1979]

It’s not really that bad. You can run some fairly big models on an Apple Silicon machine costing £2k (M4 Pro Mac Mini with 64GB RAM).