0ppxnhximxr/GLM-5.3-GGUF

Quantization vs zai-org/GLM-5.3-BF16. 0ppxnhximxr/GLM-5.3-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 440 tensors match exactly and 622 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/364, MLP 0/313, Attention 0/382, other 0/1

On the Hub · Downloads on Model Pulse