sinjab/ms-marco-MiniLM-L6-v2-Q8_0-GGUF
Not comparable yet vs cross-encoder/ms-marco-MiniLM-L6-v2. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 106/103 match), usually an architecture llama.cpp's name map doesn't cover yet.