hugging-quants/Meta-Llama-3.1-8B-Instruct-BNB-NF4
Quantization vs meta-llama/Llama-3.1-8B-Instruct. hugging-quants/Meta-Llama-3.1-8B-Instruct-BNB-NF4 is a quantized version of the other (U8/BF16).
4 other repos hold byte-for-byte identical weight files.