AmoebaNet-A (F=448)

Closed weights Google Brain 469M parameters February 2018

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
Google Brain
Organisation type
Industry
Country
United States of America
Published
5 February 2018
Authors
Esteban Real, Alok Aggarwal, Yanping Huang, Quoc V Le

What it does

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

Domain
Vision
Task
Image classification
Numerical format
FP32

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
469M

Table 2

Training data
1,150,000 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
3.9 × 10²⁰ FLOP

450 K40 GPUs for 20k models (approx. 7 days). (From Imagenet paper-data, Besiroglu et al., forthcoming)

How it was established
Hardware

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA Tesla K40s
Chips used
450
Chip-hours
75,600
Wall-clock time
168 hours (7 days)

"Each experiment ran on 450 K40 GPUs for 20k models (approx. 7 days)."

Power draw
229.2 kW
Compute cost
$11,766

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

has code, but looks like just a toy model: https://colab.research.google.com/github/google-research/google-research/blob/master/evolution/regularized_evolution_algorithm/regularized_evolution.ipynb

How it is classified

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

Record confidence
Confident
Citations
3,322

Sources

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

Reference
Regularized Evolution for Image Classifier Architecture Search
Last updated
25 May 2026

What the numbers mean

What this model is

AmoebaNet-A (F=448) was published by Google Brain, in United States of America, in February 2018. The organisation is categorised as industry.

It works in Vision, and is recorded as doing image classification.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Training and provenance

Training it took roughly 3.9 × 10²⁰ FLOP of computation, on NVIDIA Tesla K40s — a measure of what producing the model cost, not of how fast it answers.

The training set ran to roughly 1,150,000 tokens.

Answers

AmoebaNet-A (F=448) — common questions

01

Who created AmoebaNet-A (F=448)?

AmoebaNet-A (F=448) was published by Google Brain, based in United States of America, categorised as industry.

02

When was AmoebaNet-A (F=448) released?

AmoebaNet-A (F=448) was published in February 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.

03

What is AmoebaNet-A (F=448) used for?

AmoebaNet-A (F=448) works in Vision, and is recorded as handling image classification. These are the areas it was designed around; they describe intent rather than a hard boundary.

04

How much compute was used to train AmoebaNet-A (F=448)?

Around 3.9 × 10²⁰ FLOP, on NVIDIA Tesla K40s. 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.

05

What GPU do I need to run AmoebaNet-A (F=448)?

None. AmoebaNet-A (F=448) 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.

06

Is AmoebaNet-A (F=448) open source?

No. AmoebaNet-A (F=448) has not had its weights published, so it exists only as a service controlled by its owner.

07

How many parameters does AmoebaNet-A (F=448) have?

AmoebaNet-A (F=448) has 469M parameters. Table 2. 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.

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.