cnfusion/Llama-3.3-70B-Instruct-abliterated-Q2-mlx

Quantization vs huihui-ai/Llama-3.3-70B-Instruct-abliterated. cnfusion/Llama-3.3-70B-Instruct-abliterated-Q2-mlx is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse