dddsaty/phi-4-GPTQ-8bit · Hugging Face

This phi-4 model is a quantized version with Intel auto-round.

Downloads last month: 172

Safetensors

Model size

4.57B params

Tensor type

I32

·

BF16

·

FP16

·

Inference Providers NEW

Text Generation

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