1bit-MONSTER/GLM-4.7-Flash-GGUF

Quantization vs unsloth/GLM-4.7-Flash-GGUF. 1bit-MONSTER/GLM-4.7-Flash-GGUF is a GGUF quantization (Q4_K_XL) of the same weights: 286 tensors match exactly and 558 within quantization error.

Tensors changed: other 0/47, Norms 0/189, MLP 0/325, Attention 0/282, lm_head 0/1

On the Hub · Downloads on Model Pulse