Model converted to MLX and quantized to Q4. Original model https://huggingface.co/microsoft/phi-4 .

Downloads last month
7
Safetensors
Model size
2.29B params
Tensor type
FP16
·
U32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for jesusoctavioas/phi-4-MLX-Q4

Base model

microsoft/phi-4
Quantized
(135)
this model