Project AURIONAI Use-Cases Research & Innovation
Google
visionfamily

MobileNet

Google family of efficient CNNs for mobile and embedded vision, used as classifiers and as backbones for SSD, DeepLab and other edge models.

GoogleGoogleUSA
Figure from the MobileNet paper: MobileNet models can be applied to various recognition tasks for efficient on device intelligence.
Levelfamily
Classvision
Parametersnot in the notes
Contextnot in the notes
Released17 Apr 2017
Opennessunknown
Runs onmobile or NPU, CPU server, microcontroller
Statusactive

Lineage

201720182019202020212022202320242025MobileNet v1MobileNet v1, Apr 2017MobileNet v3MobileNet v3, May 2019MobileNet v4MobileNet v4, Apr 2024

2 members have no release date in the notes, so they are not on this timeline.

GoogleMobileNet v4 belongs to this familyvision16 Apr 2024
GoogleMobileNet v3 belongs to this familyvision6 May 20192.55M
GoogleMobileNet v1 belongs to this familyvision17 Apr 2017
GoogleMobileNet v5 belongs to this familyvision
GoogleMobileNet-EdgeTPU belongs to this familyvision
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

Efficient vision networks for mobile and edge devicesproduced by

Identity

Developer
Google
Family
not in the notes
Released
17 Apr 2017 sourcesannouncement page
Weights published
–
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
– sources
Active parameters
–
Checkpoint parameters
–
Note
MobileNet v1, v2 (already in AURION as mobilenet-v2), v3 (Large, Small), v4, v5 and MobileNet-EdgeTPU.
Context length
not in the notes
Input
image
Output
not in the notes
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
unknown
Licence
not in the notes sources
Access routes
open weights download, cloud marketplace
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
mobile or NPU, CPU server, microcontroller
Footprint
Edge or toolkit builds listed in: Qualcomm AI Hub, OpenVINO, STM32 model zoo, NXP eIQ model zoo, TI edge AI model zoo.
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/1704.04861 https://arxiv.org/abs/1704.04861
  2. jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json https://jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json
  3. huggingface.co/timm/mobilenetv3_small_100.lamb_in1k https://huggingface.co/timm/mobilenetv3_small_100.lamb_in1k
  4. huggingface.co/google/mobilenet_v1_1.0_224 https://huggingface.co/google/mobilenet_v1_1.0_224
  5. aihub.qualcomm.com/models/mobilenet_v3_large https://aihub.qualcomm.com/models/mobilenet_v3_large
  6. github.com/pytorch/vision/blob/main/torchvision/models/m... https://github.com/pytorch/vision/blob/main/torchvision/models/mobilenetv3.py
  7. aihub.qualcomm.com/models/mobilenet_v4 https://aihub.qualcomm.com/models/mobilenet_v4

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