ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF
Quantization vs HauhauCS/GLM-4.7-Flash-Uncensored-HauhauCS-Aggressive. ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF is a GGUF quantization (Q8_0/F16) of the same weights: 531 tensors match exactly and 313 within quantization error.
Tensors changed: lm_head 0/1, other 0/47, Norms 0/189, MLP 0/325, Attention 0/282