TensorFold/Qwen3.8-27B-MLX-6bit

Quantization vs Qwen/Qwen3.8-27B. TensorFold/Qwen3.8-27B-MLX-6bit is a quantized version of the other (U32/BF16).

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

On the Hub · Downloads on Model Pulse