mradermacher/GLM-4.7-REAP-268B-A32B-i1-GGUF
Quantization vs cerebras/GLM-4.7-REAP-268B-A32B. mradermacher/GLM-4.7-REAP-268B-A32B-i1-GGUF is a GGUF quantization (Q5_K_M) of the same weights: 734 tensors match exactly and 646 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/369, MLP 0/365, Attention 0/644, lm_head 0/1