0ppxnhximxr/GLM-5.3-Flash-GGUF

Quantization vs zai-org/GLM-5.3-Flash-BF16. 0ppxnhximxr/GLM-5.3-Flash-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 393 tensors match exactly and 317 within quantization error.

Tensors changed: Attention 0/384, lm_head 0/1, Embeddings 0/1, Norms 0/147, MLP 0/177

On the Hub · Downloads on Model Pulse