I find 27B more accurate -- maybe because I'm running at FP8 instead of NVFP4? Flash Next starts making spelling mistakes when I get to 150K context or so. Also it sometimes ignores .md file instructions. Not sure if others have found that.
What inference engine are you using for flash next?
Qwen Flash Next is just excellent, all the way to the very end of the native 262k context. (I haven’t tried YaRN scaling to 1M, so I don’t know about that.)
It always detects its spelling mistakes, btw, but it worried me. It may turn 'rm -rf ' into 'rm -rf /' one day.
Almost certainly the problem is my config, not the image.
but surely you're running it in a container?