Papers › SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot

SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot

2 Jan 2023arXiv:2301.00774archive 2025-07-28

Elias Frantar, Dan Alistarh

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples harvested from 2 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 4 samples from 1 repository, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 8 samples from 1 repository, 7 ran (7 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 9 samples that ran has no recorded date.

ist-daslab/sparsegpt officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 2 ran (2 instrument-failed) · 2 unverified report
baithebest/adagp mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Simple and Effective Pruning Approach for Large Language Models (arXiv:2306.11695; that paper's own run record: 9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
baithebest/sparsellm mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SparseLLM: Towards Global Pruning for Pre-trained Language Models (arXiv:2402.17946; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
eth-easl/deltazip mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeltaZip: Efficient Serving of Multiple Full-Model-Tuned LLMs (arXiv:2312.05215; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
nvidia/tensorrt-model-optimizer mentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 7 ran (0 instrument-failed) · 1 unverified report
nvlabs/maskllm mentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models (arXiv:2409.17481; that paper's own run record: 5 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

12 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
7ran
3unverified

Licence: 9 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

ist-daslab/sparsegpt official repository 4 samples, 2 ran (2 instrument-failed) · 2 unverified
get_bloom in 8 papers bloom.py ran · our draft was wrong Apache-2.0 (permissive) · cd666c16d4aaa66d · report fixture: signature model:str/0/str · returned MockBloomForCausalLM · level recorded 2026-09-22
get_opt in 11 papers opt.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 887f43fe08a6472d · report fixture: signature model:str/0/str · returned MockOPTForCausalLM · level recorded, date not recorded
bloom_sequential in 6 papers bloom.py unverified Apache-2.0 (permissive) · 5076786563dd8499 · report
opt_sequential in 5 papers opt.py unverified Apache-2.0 (permissive) · bf403ae47e912dc1 · report
nvidia/tensorrt-model-optimizer community (archive-listed) 8 samples, 7 ran (0 instrument-failed) · 1 unverified
get_language_model_from_vl modelopt/torch/export/model_utils.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · f1c26f01bf2f39a9 · report fixture: signature model:callable/0/?, strict:bool/0/bool · returned list · level recorded 2026-09-25
get_model_type in 10 papers modelopt/torch/export/model_utils.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · bc6cfb190b953479 · report fixture: signature model:callable/0/? · returned str · level recorded 2026-09-25
is_multimodal_model modelopt/torch/export/model_utils.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 140c6ce5087cbbce · report fixture: signature model:callable/0/? · returned bool · level recorded 2026-09-25
pad_weights modelopt/torch/export/trtllm/model_config_utils.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · f36d24bde785f7cc · report fixture: signature weights:Tensor/2/float, tp_size:int/0/int · returned Tensor · level recorded 2026-09-25
prepare_enc_dec_export_dir modelopt/torch/export/trtllm/tensorrt_llm_utils.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · e9eca650c1a383f2 · report fixture: signature tensorrt_llm_config:dict/0/?, export_root:PosixPath/0/? · returned PosixPath · level recorded 2026-09-25
student_input_bypass_fwd_hook modelopt/torch/distill/layerwise_distillation_model.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · e3133ddfe52e03a0 · report fixture: signature module:callable/0/?, input:Tensor/2/float · returned Tensor · level recorded 2026-09-25
svd in 12 papers modelopt/torch/quantization/model_calib.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 54d01cbd62cf758a · report fixture: signature weight:Tensor/2/float, rank:int/0/int · returned tuple · level recorded 2026-09-25
postprocess_amax modelopt/torch/quantization/model_quant.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 1c19ab0c6ad9a45c · report

Tasks

Common Sense ReasoningLanguage ModellingQuantizationQuestion Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Common Sense Reasoning ARC (Challenge) OPT-175B Accuracy 43.94 #44 of 54 Archive leaderboard report
Common Sense Reasoning ARC (Challenge) SparseGPT (175B, 50% Sparsity) Accuracy 41.3 #46 of 54 Archive leaderboard report
Common Sense Reasoning ARC (Challenge) SparseGPT (175B, 4:8 Sparsity) Accuracy 39.85 #47 of 54 Archive leaderboard report
Common Sense Reasoning ARC (Challenge) SparseGPT (175B, 2:4 Sparsity) Accuracy 38.99 #48 of 54 Archive leaderboard report
Common Sense Reasoning ARC (Challenge) OPT-175B (50% Sparsity) Accuracy 25.6 #54 of 54 Archive leaderboard report
Common Sense Reasoning ARC (Easy) OPT-175B Accuracy 71.04 #31 of 47 Archive leaderboard report
Common Sense Reasoning ARC (Easy) SparseGPT 175B (50% sparsity) Accuracy 69.65 #36 of 47 Archive leaderboard report
Common Sense Reasoning ARC (Easy) SparseGPT (175B, 4:8 Sparsity) Accuracy 68.35 #39 of 47 Archive leaderboard report
Common Sense Reasoning ARC (Easy) SparseGPT 175B (2:4 sparsity) Accuracy 67.08 #41 of 47 Archive leaderboard report
Common Sense Reasoning ARC (Easy) OPT 175B (50% Sparsity) Accuracy 28.03 #47 of 47 Archive leaderboard report
Language Modelling LAMBADA SparseGPT (175B, 2:4 Sparsity) Accuracy 79.47 #13 of 37 Archive leaderboard report
Language Modelling LAMBADA SparseGPT (175B, 4:8 Sparsity) Accuracy 78.77 #14 of 37 Archive leaderboard report
Language Modelling LAMBADA SparseGPT (175B, 50% Sparsity) Accuracy 76.51 #17 of 37 Archive leaderboard report
Language Modelling LAMBADA OPT-175B Accuracy 75.59 #19 of 37 Archive leaderboard report
Language Modelling LAMBADA OPT-175B (50% Sparsity) Accuracy 0.02 #33 of 37 Archive leaderboard report
Language Modelling WikiText-2 SparseGPT (175B, 50% Sparsity) Test perplexity 8.21 #1 of 38 Archive leaderboard report
Language Modelling WikiText-2 OPT-175B Test perplexity 8.34 #2 of 38 Archive leaderboard report
Language Modelling WikiText-2 SparseGPT (175B, 4:8 Sparsity) Test perplexity 8.45 #3 of 38 Archive leaderboard report
Language Modelling WikiText-2 SparseGPT (175B, 2:4 Sparsity) Test perplexity 8.73 #4 of 38 Archive leaderboard report
Language Modelling WikiText-2 OPT-175B (50% Sparsity) Test perplexity 234.77 #38 of 38 Archive leaderboard report
Question Answering PIQA OPT-175B Accuracy 81.07 #28 of 67 Archive leaderboard report
Question Answering PIQA SparseGPT 175B (50% Sparsity) Accuracy 80.63 #30 of 67 Archive leaderboard report
Question Answering PIQA SparseGPT 175B (4:8 Sparsity) Accuracy 79.54 #35 of 67 Archive leaderboard report
Question Answering PIQA SparseGPT 175B (2:4 Sparsity) Accuracy 79.54 #36 of 67 Archive leaderboard report
Question Answering PIQA OPT-175B (50% Sparsity) Accuracy 54.73 #66 of 67 Archive leaderboard report
Question Answering StoryCloze OPT-175B Accuracy 79.82 #10 of 23 Archive leaderboard report
Question Answering StoryCloze SparseGPT (175B, 50% Sparsity) Accuracy 78.87 #11 of 23 Archive leaderboard report
Question Answering StoryCloze SparseGPT (175B, 4:8 Sparsity) Accuracy 77.02 #14 of 23 Archive leaderboard report
Question Answering StoryCloze SparseGPT (175B, 2:4 Sparsity) Accuracy 76.19 #16 of 23 Archive leaderboard report
Question Answering StoryCloze OPT-175B (50% Sparsity) Accuracy 47.10 #23 of 23 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Pruning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections