Papers › Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox

Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox

15 Jun 2024arXiv:2406.12928archive 2025-07-28

Yijun Liu, Yuan Meng, Fang Wu, Shenhao Peng, Hang Yao, Chaoyu Guan, Chen Tang, Xinzhu Ma, Zhi Wang, Wenwu Zhu

Large language models (LLMs) have exhibited exciting progress in multiple scenarios, while the huge computational demands hinder their deployments in lots of real-world applications. As an effective means to reduce memory footprint and inference cost, quantization also faces challenges in performance degradation at low bit-widths. Understanding the impact of quantization on LLM capabilities, especially the generalization ability, is crucial. However, the community's main focus remains on the algorithms and models of quantization, with insufficient attention given to whether the quantized models can retain the strong generalization abilities of LLMs. In this work, we fill this gap by providing a comprehensive benchmark suite for this research topic, including an evaluation system, detailed analyses, and a general toolbox. Specifically, based on the dominant pipeline in LLM quantization, we primarily explore the impact of calibration data distribution on the generalization of quantized LLMs and conduct the benchmark using more than 40 datasets within two main scenarios. Based on this benchmark, we conduct extensive experiments with two well-known LLMs (English and Chinese) and four quantization algorithms to investigate this topic in-depth, yielding several counter-intuitive and valuable findings, e.g., models quantized using a calibration set with the same distribution as the test data are not necessarily optimal. Besides, to facilitate future research, we also release a modular-designed toolbox, which decouples the overall pipeline into several separate components, e.g., base LLM module, dataset module, quantizer module, etc. and allows subsequent researchers to easily assemble their methods through a simple configuration. Our benchmark suite is publicly available at https://github.com/TsingmaoAI/MI-optimize

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 1 repository linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 8 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: 12 samples from 1 repository, 4 ran (2 with no instrument failure; 2 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.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

tsingmaoai/mi-optimize officialmentioned in paperpytorchNOASSERTIONSyntology: 12 samples, 4 ran (2 instrument-failed) · 8 unverified 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

12 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; 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
2ran
8unverified

Licence: 12 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 tsingmaoai/mi-optimize. “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.

tsingmaoai/mi-optimize official repository 12 samples, 4 ran (2 instrument-failed) · 8 unverified
get_boss mi_optimize/datasets/load_boss.py ran licence not identified · pointer only · d89391706db541b9 · report fixture: signature task_name:str/0/str, dataset_name:str/0/str, split:str/0/str, shuffle:bool/0/bool, seed:int/0/int · returned list · level recorded 2026-09-24
get_subjects_ceval mi_optimize/datasets/load_ceval.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 40419b9c9281dcf9 · report fixture: signature subject_name:str/0/str · returned dict · level recorded 2026-09-24
get_subjects_cmmlu mi_optimize/datasets/load_cmmlu.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 91b9c29f9f68f094 · report fixture: signature subject_name:str/0/str · returned dict · level recorded 2026-09-24
load_cmmlu mi_optimize/datasets/load_cmmlu.py ran licence not identified · pointer only · cf57d949ad2d6f45 · report fixture: signature subjects:list/1/str, split:str/0/str, path:str/0/str · returned dict · level recorded 2026-09-24
get_c4 in 41 papers mi_optimize/datasets/data_loader.py unverified licence not identified · pointer only · 0f169d61e5b5e02a · report
get_calibrate_boss mi_optimize/datasets/load_boss.py unverified licence not identified · pointer only · b1df7bc50114300b · report
get_ceval mi_optimize/datasets/load_ceval.py unverified licence not identified · pointer only · d71510096bae581e · report
get_cmmlu mi_optimize/datasets/load_cmmlu.py unverified licence not identified · pointer only · 1909079fb191a012 · report
get_ptb in 43 papers mi_optimize/datasets/data_loader.py unverified licence not identified · pointer only · f6e95ffd6622a1b4 · report
get_str mi_optimize/datasets/load_boss.py unverified licence not identified · pointer only · fc292f3230d4dfd8 · report
get_wikitext2 in 78 papers mi_optimize/datasets/data_loader.py unverified licence not identified · pointer only · 05cb56deff8da528 · report
load_ceval mi_optimize/datasets/load_ceval.py unverified licence not identified · pointer only · 10664b9521178405 · report

Tasks

Quantization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASEFocusSET

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