So are locally-runnable models frozen at Qwen 3.6 now :/
Is qwen 3.6 27b the best model you can run locally at the moment? Not that I have the VRAM for it, but just curious.
Maybe, maybe not. Qwen 3.6 27B is literally just three months old. Hard to predict. Maybe it just wasn't worth making a 3.7, and after all, the 27B release was after the Plus release.
Everyone wanted open models that would challenge Opus and Codex, here, you got it.