{"url":"/method/nncf","slug":"nncf","name":"NNCF","full_name":"Neural Network Compression Framework","full_name_withheld":false,"description_markdown":"**Neural Network Compression Framework**, or **NNCF**, is a Python-based framework for neural network compression with fine-tuning. It leverages recent advances of various network compression methods and implements some of them, namely quantization, sparsity, filter pruning and binarization. These methods allow producing more hardware-friendly models that can be efficiently run on general-purpose hardware computation units (CPU, GPU) or specialized deep learning accelerators.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Neural Network Compression Framework for fast model inference","paper":"/paper/neural-network-compression-framework-for-fast","first_author":"Alexander Kozlov","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/neural-network-compression-framework-for-fast"},"source":{"url":"https://arxiv.org/abs/2002.08679v4","title":"Neural Network Compression Framework for fast model inference","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Model Compression","url":"/methods/category/model-compression","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":2,"papers_newest_first":[{"paper":"/paper/neural-collaborative-filtering-vs-matrix","title":"Neural Collaborative Filtering vs. Matrix Factorization Revisited","date":"2020-05-19","arxiv_id":"2005.09683","n_code_links":4,"syntology":null},{"paper":"/paper/neural-network-compression-framework-for-fast","title":"Neural Network Compression Framework for fast model inference","date":"2020-02-20","arxiv_id":"2002.08679","n_code_links":2,"syntology":{"ran":0,"of":2,"unverified":2,"pointer_only":0}}],"papers_shown":2,"tasks":[{"task":"/task/binarization","name":"Binarization","papers":1},{"task":null,"name":"CPU","papers":1},{"task":"/task/collaborative-filtering","name":"Collaborative Filtering","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/link-prediction","name":"Link Prediction","papers":1},{"task":"/task/neural-network-compression","name":"Neural Network Compression","papers":1},{"task":"/task/quantization","name":"Quantization","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1},{"task":"/task/model","name":"model","papers":1}],"tasks_shown":9,"n_tasks":9,"usage_by_year":[{"year":"2020","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/nncf"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}