gg000
/

Cydonia-24B-v4.1-MLX-MXFP4

Text Generation

4-bit precision

Model card Files Files and versions

gg000/Cydonia-24B-v4.1-MLX-MXFP4

Slightly faster and more memory efficient than regular 4bit.

This model gg000/Cydonia-24B-v4.1-MLX-MXFP4 was converted to MLX format from TheDrummer/Cydonia-24B-v4.1 using mlx-lm version 0.27.1.

Downloads last month: 13

Safetensors

Model size

24B params

Tensor type

U8

·

U32

·

BF16

·

Model tree for gg000/Cydonia-24B-v4.1-MLX-MXFP4

Base model

TheDrummer/Cydonia-24B-v4.1

Quantized

(18)

this model