mradermacher/UNAversal-8x7B-v1beta-i1-GGUF
Not comparable yet vs fblgit/UNAversal-8x7B-v1beta. 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.