mlx-community/llm-jp-4-32b-a3b-thinking-8bit
Quantization vs llm-jp/llm-jp-4-32b-a3b-thinking. mlx-community/llm-jp-4-32b-a3b-thinking-8bit is a quantized version of the other (U32/BF16).
Quantization vs llm-jp/llm-jp-4-32b-a3b-thinking. mlx-community/llm-jp-4-32b-a3b-thinking-8bit is a quantized version of the other (U32/BF16).