jayusop/A.X-4.0-Light-Q4_K_M-GGUF
Quantization vs skt/A.X-4.0-Light. jayusop/A.X-4.0-Light-Q4_K_M-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 141 tensors match exactly and 198 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196, lm_head 0/1