YuHaaa/Qwen2.5-72B-Instruct-abliterated-mlx-4Bit

Quantization vs huihui-ai/Qwen2.5-72B-Instruct-abliterated. YuHaaa/Qwen2.5-72B-Instruct-abliterated-mlx-4Bit is a quantized version of the other (U32/F16).

On the Hub · Downloads on Model Pulse