etemiz/Llama-3.1-405B-Inst-GGUF
Quantization vs meta-llama/Llama-3.1-405B-Instruct. etemiz/Llama-3.1-405B-Inst-GGUF is a GGUF quantization (IQ3_XXS) of the same weights: 253 tensors match exactly and 632 within quantization error.
Tensors changed: Embeddings 0/1, Attention 0/252, MLP 0/378, Norms 0/253, lm_head 0/1