PNASNet-5

Closed weights Johns Hopkins University,Google AI,Stanford University 86.1M parameters December 2017

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
Johns Hopkins University,Google AI,Stanford University
Organisation type
Academia,Industry,Academia
Country
United States of America
Published
2 December 2017
Authors
C Liu, B Zoph, M Neumann, J Shlens

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Vision
Task
Image classification

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
86.1M

Table 5

Training data
1,280,000 tokens

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
6.6 × 10¹⁹ FLOP

8 times less compute than Zoph (2018), which used 500 p100s for 4 days. (From Imagenet paper-data, Besiroglu et al., forthcoming)

How it was established
Comparison with other models

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Likely
Citations
2,140

Sources

Where this record came from and when it was last checked.

Reference
Progressive Neural Architecture Search
Last updated
25 May 2026

What the numbers mean

Where it came from

PNASNet-5 was published by Johns Hopkins University,Google AI,Stanford University, in the country recorded as United States of America, during December 2017. The category the publisher falls under is academia,Industry,Academia.

It works in the domain of Vision, and is recorded as performing the task of image classification.

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 run consumed about 6.6 × 10¹⁹ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of about 1,280,000 tokens of text.

Answers

PNASNet-5 — common questions

01

PNASNet-5— when was it released?

It was published in December 2017. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

02

PNASNet-5— what is it used for?

It works in the domain of Vision, and is recorded as handling the task of image classification. 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.

03

PNASNet-5— how much compute was used to train it?

Training consumed around 6.6 × 10¹⁹ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

04

PNASNet-5— what GPU do I need to run it?

None. This 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.

05

PNASNet-5— is it open source?

The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

06

PNASNet-5— how many parameters does it have?

It has a parameter count of 86.1M. Table 5. 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.

07

PNASNet-5— who created it?

It was published by Johns Hopkins University,Google AI,Stanford University, based in United States of America, an organisation categorised as academia,Industry,Academia.

Source

Original publication

Record last updated 25 May 2026

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.