Hugging Face's logo

marcusmi4n
/
phi-3.5-mini-instruct-quantized-qnn

ONNX
phi3
custom_code
8-bit precision
onnx_dynamic_int8
Model card Files
xet
Community
phi-3.5-mini-instruct-quantized-qnn / _model_model_Constant_attr__value

Commit History

Upload Phi-3.5 quantized for QNN deployment (50% compression, tested & verified)
597cb25
verified

marcusmi4n commited on