mlx-community/LFM2.5-1.2B-Thinking-4bit
Quantization vs LiquidAI/LFM2.5-1.2B-Thinking. mlx-community/LFM2.5-1.2B-Thinking-4bit is a quantized version of the other (U32/BF16).
2 other repos hold byte-for-byte identical weight files.
Quantization vs LiquidAI/LFM2.5-1.2B-Thinking. mlx-community/LFM2.5-1.2B-Thinking-4bit is a quantized version of the other (U32/BF16).
2 other repos hold byte-for-byte identical weight files.