Xception

Closed weights Google 22.9M parameters October 2016

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
Organisation type
Industry
Country
United States of America
Published
7 October 2016
Authors
François Chollet

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
22.9M

Table 3

Training data
350,000,000 tokens

"JFT is an internal Google dataset for large-scale image classification dataset, first introduced by Hinton et al. in [5], which comprises over 350 million high-resolution images annotated with labels from a set of 17,000 classes. To evaluate the performance of a model trained on JFT, we use an auxiliary dataset, FastEval14k"

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
4.4 × 10²⁰ FLOP

60 K80 GPUs * 30 days * 8.5 TFLOPS/GPU * 0.33 utilization = 4.36e20 Authors of "AI and Memory Wall" (https://github.com/amirgholami/ai_and_memory_wall) estimated model's training compute as 450,000 PFLOP = 4.5*10^20 FLOP

How it was established
Hardware,Third-party estimation

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 K80
Chips used
60
Chip-hours
43,200
Wall-clock time
720 hours (30 days)

"while the JFT experiments took over one month each."

Power draw
37.8 kW
Compute cost
$13,109

How it is classified

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

Frontier model
Yes
Why it is tracked
Highly cited
Record confidence
Confident
Citations
17,674

Sources

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

Reference
Xception: Deep Learning with Depthwise Separable Convolutions
Last updated
25 May 2026

What the numbers mean

What this model is

Xception was published by Google, in the country recorded as United States of America, during October 2016. The publishing organisation is categorised as industry.

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.

Training and provenance

Training it took a computation budget of roughly 4.4 × 10²⁰ FLOP, on hardware recorded as NVIDIA Tesla K80. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Training consumed a corpus of around 350,000,000 tokens of text.

The reason it appears in this catalogue at all: highly cited.

Answers

Xception — common questions

01

Xception— when was it released?

It was published in October 2016. 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

Xception— what is it used for?

It works in the domain of Vision, and is recorded as handling the task of image classification. These are the areas it was designed around; they describe intent rather than a hard boundary.

03

Xception— how much compute was used to train it?

Training consumed around 4.4 × 10²⁰ FLOP, on hardware recorded as NVIDIA Tesla K80. 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

Xception— 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

Xception— 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

Xception— how many parameters does it have?

It has a parameter count of 22.9M. Table 3. 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

Xception— who created it?

It was published by Google, based in United States of America, an organisation categorised as industry.

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.