TheBloke/Instruct_Mixtral-8x7B-v0.1_Dolly15K-GGUF
Not comparable yet vs Brillibits/Instruct_Mixtral-8x7B-v0.1_Dolly15K. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (227 of 995/995 match), usually an architecture llama.cpp's name map doesn't cover yet.