MobileNetV2
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Organisation type
- Industry
- Country
- United States of America
- Published
- 18 June 2018
- Authors
- M Sandler, A Howard, M Zhu
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Object detection, Image classification, Image segmentation
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 3.4M
- Training data
- 1,280,000 tokens
Rados
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- Highly cited
- Citations
- 16,899
Sources
Where this record came from and when it was last checked.
- Reference
- MobileNetV2: Inverted Residuals and Linear Bottlenecks
- Last updated
- 28 November 2025
What the numbers mean
About this model
MobileNetV2 was published by Google, in United States of America, in June 2018. The organisation is categorised as industry.
It works in Vision, and is recorded as doing object detection, Image classification, Image segmentation.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
What went into building it
The training set ran to roughly 1,280,000 tokens.
Its inclusion criterion is highly cited.
Answers
MobileNetV2 — common questions
How many parameters does MobileNetV2 have?
MobileNetV2 has 3.4M parameters. Rados. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
Who created MobileNetV2?
MobileNetV2 was published by Google, based in United States of America, categorised as industry.
When was MobileNetV2 released?
MobileNetV2 was published in June 2018. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is MobileNetV2 used for?
MobileNetV2 works in Vision, and is recorded as handling object detection, Image classification, Image segmentation. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
What GPU do I need to run MobileNetV2?
None. MobileNetV2 is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
Is MobileNetV2 open source?
The licensing for MobileNetV2 was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.