Atomic-Germ/Qwen3.8-Whittle-MoE-27B-A17.8B-GGUF
Not comparable yet vs Qwen/Qwen3.8-27B. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (563 of 1199/1171 match), usually an architecture llama.cpp's name map doesn't cover yet.