gg000
/

Cydonia-R1-24B-v4.1-MLX-MXFP4

Text Generation

4-bit precision

Model card Files Files and versions

gg000/Cydonia-R1-24B-v4.1-MLX-MXFP4

4.25 bits per weight.

This model gg000/Cydonia-R1-24B-v4.1-MLX-MXFP4 was converted to MLX format from TheDrummer/Cydonia-R1-24B-v4.1 using mlx-lm version 0.28.2.

Downloads last month: 25

Safetensors

Model size

24B params

Tensor type

U8

·

U32

·

BF16

·

Model tree for gg000/Cydonia-R1-24B-v4.1-MLX-MXFP4

Base model

TheDrummer/Cydonia-R1-24B-v4.1

Quantized

(11)

this model