mlx-community/Llama-3.2-3B-Instruct-abliterated-6bit
Quantization vs huihui-ai/Llama-3.2-3B-Instruct-abliterated. mlx-community/Llama-3.2-3B-Instruct-abliterated-6bit is a quantized version of the other (U32/F16).
Quantization vs huihui-ai/Llama-3.2-3B-Instruct-abliterated. mlx-community/Llama-3.2-3B-Instruct-abliterated-6bit is a quantized version of the other (U32/F16).