{"work":{"id":"c299c96a-ab17-4fd6-9c67-201f8d8f1138","openalex_id":"https://openalex.org/W4313484599","doi":"10.48550/arxiv.2301.00774","arxiv_id":"2301.00774","raw_key":null,"title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","authors":null,"authors_text":"Elias Frantar and Dan Alistarh","year":2023,"venue":"cs.LG","abstract":"We show for the first time that large-scale generative pretrained transformer (GPT) family models can be pruned to at least 50% sparsity in one-shot, without any retraining, at minimal loss of accuracy. This is achieved via a new pruning method called SparseGPT, specifically designed to work efficiently and accurately on massive GPT-family models. We can execute SparseGPT on the largest available open-source models, OPT-175B and BLOOM-176B, in under 4.5 hours, and can reach 60% unstructured sparsity with negligible increase in perplexity: remarkably, more than 100 billion weights from these models can be ignored at inference time. SparseGPT generalizes to semi-structured (2:4 and 4:8) patterns, and is compatible with weight quantization approaches. The code is available at: https://github.com/IST-DASLab/sparsegpt.","external_url":"https://arxiv.org/abs/2301.00774","cited_by_count":69,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2301.00774","created_at":"2026-05-10T23:45:54.112652+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Sparsegpt: Massive language models can be accurately pruned in one-shot","render_title":"Sparsegpt: Massive language models can be accurately pruned in one-shot"},"hub":{"state":{"work_id":"c299c96a-ab17-4fd6-9c67-201f8d8f1138","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":22,"external_cited_by_count":69,"distinct_field_count":8,"first_pith_cited_at":"2023-06-24T20:11:14+00:00","last_pith_cited_at":"2026-07-08T15:51:57+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-21T18:19:48.113607+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3}],"polarity_counts":[{"context_polarity":"background","n":2},{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}