mradermacher/GLM-4.6-Derestricted-v3-i1-GGUF
Not comparable yet vs ArliAI/GLM-4.6-Derestricted-v3. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 44689/2000 match), usually an architecture llama.cpp's name map doesn't cover yet.