1024m
/

Phi-3.5-MoE-4bit-fp4

4-bit precision

Model card Files Files and versions Community

No model card

New: Create and edit this model card directly on the website!

Contribute a Model Card

Downloads last month: 98

Safetensors

Model size

21.7B params

Tensor type

F32

·

FP16

·

U8

·

Inference API

Unable to determine this model's library. Check the docs .

Collection including 1024m/Phi-3.5-MoE-4bit-fp4

4bit quantized LLMs

4bit quantized versions to run locally & on free colab/kaggle GPUs • 4 items • Updated 24 days ago • 1