Depends of what you want to do!? Just for testing most of the 7B model are a good compromise between quality and performance (speak execution time)
What I think is, from my limited understanding about this field, if smaller models can run on consumer hardware reliably and speedily that would be a game changer.
Not really. Inference is never "free" unless you cache the result (which is just a static output) or unless you reduce complexity (which yields procedurally less-usable outputs).