mradermacher/GLM-4.7-GGUF

Quantization vs zai-org/GLM-4.7. mradermacher/GLM-4.7-GGUF is a GGUF quantization (IQ4_XS) of the same weights: 745 tensors match exactly and 656 within quantization error.

Tensors changed: Embeddings 0/2, Norms 0/376, MLP 0/369, Attention 0/651, lm_head 0/1, other 0/2

On the Hub · Downloads on Model Pulse