TheBloke/openbuddy-mixtral-7bx8-v16.3-32k-GGUF
Not comparable yet vs OpenBuddy/openbuddy-mixtral-7bx8-v16.3-32k. 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.