Task
Other
P
nvidia/Phi-4-reasoning-plus-NVFP4
Other·nvidia· 427.6K· 11
Model Optimizer
mit
Other
7.8B params
base_model:microsoft/Phi-4-reasoning-plusbase_model:quantized:microsoft/Phi-4-reasoning-pluslicense:mit
Description: The NVIDIA Phi-4-reasoning-plus FP4 model is the quantized version of Microsoft’s Phi-4-reasoning-plus model, which is a multimodal foundation model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA Phi-4-reasoning-plus FP4 model is quantized with TensorRT Model Optimizer.
# pull & run locally
pip install mlforge-sdk && mlforge pull nvidia/Phi-4-reasoning-plus-NVFP4
pip install mlforge-sdk && mlforge pull nvidia/Phi-4-reasoning-plus-NVFP4
Model details
Provider
nvidia
Framework
Model Optimizer
Parameters
7.8B
Size
9.1 GB
License
mit
Downloads
427.6K
Likes
11
Updated
2025-09-05
About nvidia/Phi-4-reasoning-plus-NVFP4
Description: The NVIDIA Phi-4-reasoning-plus FP4 model is the quantized version of Microsoft’s Phi-4-reasoning-plus model, which is a multimodal foundation model that uses an optimized transformer architecture. For more information, please check here. The NVIDIA Phi-4-reasoning-plus FP4 model is quantized with TensorRT Model Optimizer.