Papers › ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers

ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers

28 Sep 2023arXiv:2309.16119archive 2025-07-28

Junjie Yin, Jiahao Dong, Yingheng Wang, Christopher De Sa, Volodymyr Kuleshov

We propose a memory-efficient finetuning algorithm for large language models (LLMs) that supports finetuning LLMs with 65B parameters in 2/3/4-bit precision on as little as one 24GB GPU. Our method, modular low-rank adaptation (ModuLoRA), integrates any user-specified weight quantizer with finetuning via low-rank adapters (LoRAs). Our approach relies on a simple quantization-agnostic backward pass that adaptively materializes low-precision LLM weights from a custom black-box quantization module. This approach enables finetuning 2-bit and 3-bit LLMs for the first time -- leveraging state-of-the-art 2-bit QuIP\# quantization and 3-bit OPTQ quantization -- outperforming finetuning that relies on less sophisticated 4-bit and 8-bit methods. In our experiments, \lplora~attains competitive performance on text classification, natural language inference, and instruction following tasks using significantly less memory than existing approaches, and we also surpass the state-of-the-art ROUGE score on a popular summarization task. We release \lplora~together with a series of low-precision models as part of \llmtune, a user-friendly library for quantizing, running, and finetuning LLMs on consumer GPUs.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2309.16119")

Code

Syntology Ran 5 of 9 code samples harvested from 2 repositories linked to this paper; 4 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 9 samples from 2 repositories, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

kuleshov-group/llmtools officialmentioned in papermentioned on GitHubpytorch report
kuleshov-group/modulora-experiment officialmentioned in papermentioned on GitHubpytorch report
kuleshov-group/llmtune mentioned on GitHubpytorch 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.

Code Syntology ran Syntology

9 samples harvested; 5 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
3ran
4unverified

Licence: 8 of the 9 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; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

find_layers kuleshov-group/llmtools/llmtools/utils.py official repository ran · our draft was wrong no licence file found · pointer only · a9e7f2cdf016b88b · report
load_llm kuleshov-group/llmtools/llmtools/executor.py official repository ran no licence file found · pointer only · 0b601a0502930f6a · report
load_tokenizer kuleshov-group/llmtools/llmtools/executor.py official repository ran no licence file found · pointer only · a2178676d3e7abdd · report
preprocess_logits_for_metrics kuleshov-group/modulora-experiment/finetune/samsum-llama/train_samsum_4bit.py official repository ran · our draft was wrong MIT (permissive) · bd72bc50b587388e · report
to_half_precision kuleshov-group/llmtools/llmtools/utils.py official repository ran no licence file found · pointer only · ce032426a6ed928c · report
load_adapter kuleshov-group/llmtools/llmtools/executor.py official repository unverified no licence file found · pointer only · cf26abc9397a7e53 · report
load_bloom_unquantized kuleshov-group/llmtools/llmtools/llms/bloom/model.py official repository unverified no licence file found · pointer only · c127added3419e2f · report
load_llama2_unquantized kuleshov-group/llmtools/llmtools/llms/llama2/model.py official repository unverified no licence file found · pointer only · 36c4edd08c263380 · report
load_llama_unquantized kuleshov-group/llmtools/llmtools/llms/llama/model.py official repository unverified no licence file found · pointer only · de4a6d2be23fd557 · report

Tasks

Instruction FollowingNatural Language InferenceQuantizationText Classificationtext-classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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