That's useful to know. My experiments with the 4bit 7B currently tagged for use on ollama are not going well at all. Lots of refusals and junk. Downloading 7b-instruct-fp16 now! :-) (Update: Yes, much better, though much slower too, of course.)
FYI we have an experimental 4.5-bit format (NUQ) in gemma.cpp, our C++ inference engine, which from my testing works reasonably well.
Thanks, I'm going to give that a go too. The good news is the very latest Ollama update (0.1.27) has resolved things (though I also had to redownload the quant model for 7B).