mlx-community/Qwen2.5-7B-Instruct-1M-8bit
Quantization vs Qwen/Qwen2.5-7B-Instruct-1M. mlx-community/Qwen2.5-7B-Instruct-1M-8bit is a quantized version of the other (U32/F16).
Quantization vs Qwen/Qwen2.5-7B-Instruct-1M. mlx-community/Qwen2.5-7B-Instruct-1M-8bit is a quantized version of the other (U32/F16).