masahiroid/llm-jp-4-8b-thinking-4bit-mlx

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

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse