mradermacher/Nethena-MLewd-Xwin-23B-GGUF
Quantization vs Undi95/Nethena-MLewd-Xwin-23B. mradermacher/Nethena-MLewd-Xwin-23B-GGUF is a GGUF quantization (Q8_0) of the same weights: 144 tensors match exactly and 498 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/143, MLP 0/213, Attention 0/284, lm_head 0/1