I hope that this brings out a bunch more real study about the qualitative metrics of these models, both to increase the confidence and accessibility of local LLMs, but also to reduce the blind worship that seems to be propagating about their miracle work in all domains.

I've been using the model for a few days and it really is incredibly strong. It gives anybody with access significant power. You can't deny that. I've used all large models (~1T) to get a feel for the difference, and it's real.