Question for those using local models for coding assistance: how well do the best locally runnable models (running on a laptop with a GPU) work for the easy case:

Writing short runs of code and tests after I give an clear description of the expected behavior (because I have done the homework). I want to save the keystrokes and the mental energy spent on bookkeeping code, not have it think about the big problem for me.

Think short algorithms/transformations/script, and "smart" auto complete.

No writing entire systems/features or creating heavily interpolated things due to underspecified prompts - I'm not interested in those.