This model was converted to MLX format from z-lab/Qwen3.6-27B-DFlash.

Code To Quantify This Model

from mlx_vlm import convert

convert(
    hf_path="/Volumes/original_model_path/Qwen3.6-27B-DFlash",
    mlx_path="/Volumes/quantized_model_path/Qwen3.6-27B-DFlash-MLX-6bit",
    quantize=True,
    q_bits=6,
    q_group_size=32
)

Downloads last month: 55

Safetensors

Model size

2B params

Tensor type

U32

BF16

MLX

Hardware compatibility

6-bit

Model tree for funnygeeker/Qwen3.6-27B-DFlash-MLX-6bit

Base model

z-lab/Qwen3.6-27B-DFlash

Quantized

(19)

this model