{"library":"nncf","type":"library","category":null,"description":"The Neural Networks Compression Framework (NNCF) is a Python library developed by Intel as part of the OpenVINO Toolkit, providing advanced algorithms for optimizing deep learning models for faster and smaller inference. It supports models from PyTorch, TensorFlow (deprecated), ONNX, and OpenVINO IR formats, offering techniques such as Post-Training Quantization, Quantization-Aware Training, Weight Compression, and Pruning. NNCF is actively maintained with frequent releases, with the current stable version being 3.1.0.","language":"python","status":"active","version":"3.1.0","tags":["AI/ML","model compression","quantization","pruning","OpenVINO","PyTorch","TensorFlow","ONNX"],"install":[{"cmd":"pip install nncf","imports":["import nncf\nquantized_model = nncf.quantize(model, calibration_dataset)","import nncf\ncompressed_model = nncf.compress_weights(model)","import nncf\npruned_model = nncf.prune(model, config)","from nncf import NNCFConfig","from nncf import ModelType","from nncf import QuantizationPreset","from nncf.quantization.advanced_parameters import AdvancedQuantizationParameters","from nncf import IgnoredScope","from nncf.torch import get_config","from nncf.torch import load_from_config"]},{"cmd":"pip install nncf[openvino]","imports":[]},{"cmd":"pip install nncf[torch]","imports":[]},{"cmd":"pip install nncf[tensorflow]","imports":[]}],"homepage":null,"github":"https://github.com/openvinotoolkit/nncf","docs":null,"changelog":null,"pypi":"https://pypi.org/project/nncf/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":50,"avg_install_s":15.4,"avg_import_s":2.72,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/nncf/compatibility"},"provenance":{"verified_status":"install_fail","verified_at":"Sun Jun 28","last_verified":"Sun Jun 28","next_check":"Thu Jul 09","install_tag":null}}