Papers › MobileNetV4 -- Universal Models for the Mobile Ecosystem
MobileNetV4 -- Universal Models for the Mobile Ecosystem
Danfeng Qin, Chas Leichner, Manolis Delakis, Marco Fornoni, Shixin Luo, Fan Yang, Weijun Wang, Colby Banbury, Chengxi Ye, Berkin Akin, Vaibhav Aggarwal, Tenghui Zhu, Daniele Moro, Andrew Howard
We present the latest generation of MobileNets, known as MobileNetV4 (MNv4), featuring universally efficient architecture designs for mobile devices. At its core, we introduce the Universal Inverted Bottleneck (UIB) search block, a unified and flexible structure that merges Inverted Bottleneck (IB), ConvNext, Feed Forward Network (FFN), and a novel Extra Depthwise (ExtraDW) variant. Alongside UIB, we present Mobile MQA, an attention block tailored for mobile accelerators, delivering a significant 39% speedup. An optimized neural architecture search (NAS) recipe is also introduced which improves MNv4 search effectiveness. The integration of UIB, Mobile MQA and the refined NAS recipe results in a new suite of MNv4 models that are mostly Pareto optimal across mobile CPUs, DSPs, GPUs, as well as specialized accelerators like Apple Neural Engine and Google Pixel EdgeTPU - a characteristic not found in any other models tested. Finally, to further boost accuracy, we introduce a novel distillation technique. Enhanced by this technique, our MNv4-Hybrid-Large model delivers 87% ImageNet-1K accuracy, with a Pixel 8 EdgeTPU runtime of just 3.8ms.
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):
get_harvested_code_for_paper(arxiv_id="2404.10518")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2404.10518", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2404.10518")
Code
No sample from the archive's official repository (tensorflow/models) is linked to this paper; the 13 samples below come from 4 community repositories. Syntology harvested code from tensorflow/models for 4 other papers.
tensorflow/models: Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.
Syntology 13 code samples harvested from 4 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 13 samples from 4 repositories, 11 ran (8 with no instrument failure; 3 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 2 of its repositories that Syntology harvested for other papers:
- tensorflow/models, official repository: harvested for 4 other papers, listed under the repository
- huggingface/pytorch-image-models, community (archive-listed): harvested for another paper, listed under the repository
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.
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
13 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 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.
Licence: 2 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 4 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. “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.
067715c0c5734d87 · report
fixture: signature inp:int/0/int, oup:int/0/int, kernel_size:int/0/int, stride:int/0/int, groups:int/0/int, bias:bool/0/bool, norm:bool/0/bool, act:bool/0/bool · returned Sequential · level recorded 2026-09-22 6b65b07f03530a4d · report
fixture: signature value:float/0/float, divisor:int/0/int, min_value:NoneType/0/?, round_down_protect:bool/0/bool · returned int · level recorded 2026-09-22 a7ca97f43224d68c · report
ce856d9e51a3df05 · report
fixture: signature output:ndarray/2/float, target:ndarray/1/int · returned tuple · level recorded 2026-09-24 24400bc088ed228d · report
fixture: signature v:int/0/int, divisor:int/0/int, min_value:NoneType/0/?, round_limit:float/0/float · returned int · level recorded 2026-09-22 968810e99c2743be · report
fixture: signature preds:ndarray/2/float · returned ndarray · level recorded 2026-09-24 3858599774ed62d7 · report
fixture: signature group_size:int/0/int, channels:int/0/int · returned int · level recorded 2026-09-24 57c0e0444e26c7e2 · report
fixture: signature model:callable/0/?, inplace:bool/0/bool · returned TestModel · level recorded 2026-09-24 65913dcf1b9ca4d1 · report
fixture: signature kwargs:dict/0/?, default:str/0/str · returned type · level recorded 2026-09-24 ad5c779c4dbc8362 · report
fixture: signature kwargs:dict/0/? · returned dict · level recorded 2026-09-25 0e20d40db79fb5c0 · report
fixture: signature block_specs:list/1/BlockSpec · returned list · level recorded 2026-09-22 231ab9d94ccd8ac2 · report
fixture: signature value:float/0/float, divisor:int/0/int, min_value:NoneType/0/?, round_down_protect:bool/0/bool · returned int · level recorded 2026-09-22 Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Classification | ImageNet | MNv4-Hybrid-L | Top 1 Accuracy | 83.4% | #426 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | MNv4-Conv-L | Top 1 Accuracy | 82.9% | #485 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | MNv4-Hybrid-M | Top 1 Accuracy | 80.7% | #684 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | MNv4-Conv-M | Top 1 Accuracy | 79.9% | #729 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | MNv4-Conv-S | Top 1 Accuracy | 73.8% | #984 of 1060 | 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
Introduced by this paper: MobileNet-V4
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