DevQuasar-4/THUDM.glm-4-9b-chat-1m-GGUF
Not comparable yet vs zai-org/glm-4-9b-chat-1m. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (80 of 284/283 match), usually an architecture llama.cpp's name map doesn't cover yet.