If you want the exact pack I built for this - https://huggingface.co/Avifenesh/Qwen3.8-27B-NVFP4-MTP-GGUF
Head stays native NVFP4. The ranks list is q38-ranks-sxc32768.gguf.txt on that repo if you want the trimmed-head path instead of a separate GGUF head.
Yeah that tracks. I kept thinking a fatter head would just be more accurate. Same trap. When I requantized the trimmed head to NVFP4, acceptance didn't move. Zero. The draft only has to land tokens the target will take, not match the BF16 parent. Your 48.3 to 33.1 from bumping NVFP4 up to Q5_K/Q6_K is the same movie the other way. I'll read the writeup.
