It’s unbearably slow, for sure. Not nearly as slow as Kimi K2.6 though. I’m trying to like 4.8 but I may go back to 4.6 again. Definitely won’t ever be using 4.7. 4.8 took a shortcut today. There was an error in my local LLM’s relay of thinking text. So it brilliantly decided to turn thinking off, neutering the model. Had to revert that nerf. That’s the same lazy behavior as 4.7. 4.6 would never.
Curious why you prefer 4.6 over 4.7