MaziyarPanahi/Llama3-12B-wwe-GGUF
Quantization vs mergekit-community/Llama3-12B-wwe. MaziyarPanahi/Llama3-12B-wwe-GGUF is a GGUF quantization (Q8_0) of the same weights: 117 tensors match exactly and 408 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/117, MLP 0/174, Attention 0/232, lm_head 0/1