mradermacher/XuanYuan-70B-Chat-GGUF
Quantization vs Duxiaoman-DI/XuanYuan-70B-Chat. mradermacher/XuanYuan-70B-Chat-GGUF is a GGUF quantization (Q5_K_M) of the same weights: 162 tensors match exactly and 561 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 0/320, lm_head 0/1