promzeus/gh0stx-glm46-gb10-GGUF

Quantization vs zai-org/GLM-4.6. promzeus/gh0stx-glm46-gb10-GGUF is a GGUF quantization (Q5K) of the same weights: 745 tensors match exactly and 654 within quantization error.

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

On the Hub · Downloads on Model Pulse