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
18
Safetensors
Model size
24B params
Tensor type
U8
U32
BF16
MLX
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

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

Quantized
(14)
this model