mlx-community/Llama-3.1-8B-Instruct-4bit
Quantization vs meta-llama/Llama-3.1-8B-Instruct. mlx-community/Llama-3.1-8B-Instruct-4bit is a quantized version of the other (U32/F16).
2 other repos hold byte-for-byte identical weight files.
Quantization vs meta-llama/Llama-3.1-8B-Instruct. mlx-community/Llama-3.1-8B-Instruct-4bit is a quantized version of the other (U32/F16).
2 other repos hold byte-for-byte identical weight files.