AlphaX-1

Closed weights Facebook AI Research,Brown University 5.4M parameters October 2019

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
Facebook AI Research,Brown University
Organisation type
Industry,Academia
Country
United States of America, France
Published
2 October 2019
Authors
Linnan Wang, Yiyang Zhao, Yuu Jinnai, Yuandong Tian, Rodrigo Fonseca1

What it does

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

Domain
Vision
Task
Neural architecture search for computer vision, Image classification, Object detection, Image captioning

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
5.4M

Table 3: multiadds for AlphaX-1 579M, parameters 5.4M

Training data
61,280,000 tokens

Standard image net training size, not otherwise specified

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
8.9 × 10¹⁷ FLOP

" Our models for ImageNet use polynomial learning rate schedule, starting with 0.05 and decay through 200 epochs." 1280000 images * 200 epochs *3 forward-backward adjustment * 1158000000 forward FLOP =889344000000000000

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 GeForce GTX 1080 Ti

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
Open (non-commercial)

code, no license specified: https://github.com/linnanwang/AlphaX-NASBench101 training: https://github.com/linnanwang/AlphaX-NASBench101/blob/master/net_training.py

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
SOTA improvement

"In 12 GPU days and 1000 samples, AlphaX found an architecture that reaches 97.84\% top-1 accuracy on CIFAR-10, and 75.5\% top-1 accuracy on ImageNet, exceeding SOTA NAS methods in both the accuracy and sampling efficiency"

Record confidence
Confident
Citations
100

Sources

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

Reference
AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search
Last updated
25 May 2026

What the numbers mean

About this model

AlphaX-1 was published by Facebook AI Research,Brown University, in United States of America, in October 2019. It comes out of industry,Academia.

It works in Vision, and is recorded as doing neural architecture search for computer vision, Image classification, Object detection, Image captioning.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Training and provenance

Producing it required around 8.9 × 10¹⁷ FLOP of arithmetic, on NVIDIA GeForce GTX 1080 Ti, which is a statement about the training budget rather than about inference.

Around 61,280,000 tokens went into training it.

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Answers

AlphaX-1 — common questions

01

What GPU do I need to run AlphaX-1?

None. AlphaX-1 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.

02

Is AlphaX-1 open source?

No. AlphaX-1 has not had its weights published, so it exists only as a service controlled by its owner.

03

How many parameters does AlphaX-1 have?

AlphaX-1 has 5.4M parameters. Table 3: multiadds for AlphaX-1 579M, parameters 5.4M. 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.

04

Who created AlphaX-1?

AlphaX-1 was published by Facebook AI Research,Brown University, based in United States of America, categorised as industry,Academia.

05

When was AlphaX-1 released?

AlphaX-1 was published in October 2019. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

What is AlphaX-1 used for?

AlphaX-1 works in Vision, and is recorded as handling neural architecture search for computer vision, Image classification, Object detection, Image captioning. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

07

How much compute was used to train AlphaX-1?

Around 8.9 × 10¹⁷ FLOP, on NVIDIA GeForce GTX 1080 Ti. 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.

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.