TheBloke/Mixtral-Fusion-4x7B-Instruct-v0.1-GGUF
Not comparable yet vs mmnga/Mixtral-Fusion-4x7B-Instruct-v0.1. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (227 of 611/611 match), usually an architecture llama.cpp's name map doesn't cover yet.