I disagree, based on having used it extensively over the last week. I find it to be at least as strong as Sonnet 4.5 and 5.2-Codex on the majority of tasks, often better. Note that even among the big 3, each of them has a domain where they're better than the other two. It's not better than Codex (x-)high at debugging non-UI code - but neither is Opus or Gemini. It's not better than Gemini at UI design - but neither is Opus or Codex. It's not better than Opus at tool usage and delegation - but neither is Gemini or Codex.
Yeah Kimi-K2.5 is the first open weights model that actually feels competitive with the closed models, and I've tried a lot of them now.
Same, I'm still not sure where it shines though. In each of the three big domains I named, the respective top performing closed model still seems to have the edge. That keeps me from reaching for it more often. Fantastic all-rounder for sure.
What hardware are you running it on?
I'm not running it locally, just using cloud inference. The people I know who do use RTX 6000s, picking the quant based on how many of them they've got. Chained M3 ultra setups are fine to play around with but too slow for actual use as a dev.