sirus/Qwen3.8-27B-heretic-ara-MXFP6-MXFP8-DFlash2-GGUF
Not comparable yet vs heretic-org/Qwen3.8-27B-heretic-ara. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (30 of 1199/81 match), usually an architecture llama.cpp's name map doesn't cover yet.