mradermacher/Nile-Chat-12B-GGUF
Quantization vs MBZUAI-Paris/Nile-Chat-12B. mradermacher/Nile-Chat-12B-GGUF is a GGUF quantization (Q8_0) of the same weights: 289 tensors match exactly and 337 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192