gg000/Cydonia-R1-24B-v4.1-MLX-mixed-4bit

5.351 bits per weight.

This model gg000/Cydonia-R1-24B-v4.1-MLX-mixed-4bit was converted to MLX format from TheDrummer/Cydonia-R1-24B-v4.1 using mlx-lm version 0.28.2.

Downloads last month
3
Safetensors
Model size
24B params
Tensor type
BF16
·
U32
·
MLX
Hardware compatibility
Log In to view the estimation

4-bit

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

Model tree for gg000/Cydonia-R1-24B-v4.1-MLX-mixed-4bit

Quantized
(11)
this model