Project AURIONAI Use-Cases Research & Innovation
vision

MobileNet v3

MobileNet found by hardware-aware architecture search, from the paper "Searching for MobileNetV3".

GoogleGoogleUSAMobileNetFamily
Google
Levelvariant
Classvision
Parameters2.55M
Contextnot in the notes
Released6 May 2019
Opennessopen weights permissive
Runs onnot in the notes
Statusactive

Lineage

successor
MobileNet v1 to MobileNet v2: successor, high confidenceMobileNet v2 to MobileNet v3: successor, high confidenceMobileNet v3 to MobileNet v4: successor, high confidenceMobileNet v1MobileNet v1Google, Apr 2017MobileNet v2MobileNet v2MobileNet v3MobileNet v3Google, May 2019MobileNet v4MobileNet v4Google, Apr 2024
MobileNet v2 is the parent (successor)high confidencenotes
GoogleMobileNet v4 is a child (successor)high confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 4 models. Confidence and evidence are the notes' own.

R&D Topics

Efficient vision networks for mobile and edge devicesproduced by

Identity

Developer
Google
Family
MobileNet
Released
6 May 2019 sourcesannouncement page
Weights published
16 Dec 2022
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
CNN
Total parameters
2.55M sources
Active parameters
–
Checkpoint parameters
–
Note
Large and Small; LR-ASPP segmentation head and SSDLite detector come from the same paper.
Context length
not in the notes
Input
image
Output
labels and boxes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights permissive
Licence
Apache License 2.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/1905.02244 https://arxiv.org/abs/1905.02244
  2. huggingface.co/timm/mobilenetv3_small_100.lamb_in1k https://huggingface.co/timm/mobilenetv3_small_100.lamb_in1k

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MobileNet v3", https://aurion.semai.id/models/google-mobilenet-v3/, records of October 2026.