TensorFold/Ling-3.0-flash-MLX-4bit

Quantization vs inclusionAI/Ling-3.0-flash. TensorFold/Ling-3.0-flash-MLX-4bit 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