Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
dddsaty
/
phi-4-GPTQ-8bit
like
1
Text Generation
Transformers
Safetensors
English
phi3
phi
nlp
math
code
chat
conversational
custom_code
text-generation-inference
8-bit precision
gptq
arxiv:
2412.08905
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
This phi-4 model is a quantized version with Intel
auto-round
.
Phi-4 quantization and inference speedup
Phi-4 Technical Report
Phi-4 HuggingFace Repo
Downloads last month
332
Safetensors
Model size
5B params
Tensor type
I32
路
BF16
路
F16
路
Chat template
Files info
Inference Providers
NEW
Text Generation
This model isn't deployed by any Inference Provider.
馃檵
Ask for provider support
Model tree for
dddsaty/phi-4-GPTQ-8bit
Finetunes
1 model
