bibproj/GLM-5.3-Q4K-ds4-gguf

Quantization vs zai-org/GLM-5.3-BF16. bibproj/GLM-5.3-Q4K-ds4-gguf is a GGUF quantization (Q4_K_ROUTEDQ4K) of the same weights: 462 tensors match exactly and 600 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