mradermacher/GLM-4.5-Iceblink-v3-106B-A12B-GGUF
Quantization vs zerofata/GLM-4.5-Iceblink-v3-106B-A12B. mradermacher/GLM-4.5-Iceblink-v3-106B-A12B-GGUF is a GGUF quantization (Q8_0) of the same weights: 276 tensors match exactly and 324 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/93, MLP 0/183, Attention 0/322