mradermacher/Llama-3-16B-GGUF
Quantization vs MaziyarPanahi/Llama-3-16B. mradermacher/Llama-3-16B-GGUF is a GGUF quantization (Q8_0) of the same weights: 145 tensors match exactly and 506 within quantization error.
Tensors changed: MLP 0/216, Norms 0/145, Attention 0/288, Embeddings 0/1, lm_head 0/1