SPN (ImageNet 128)
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,DeepMind
- Organisation type
- Industry,Industry
- Country
- United States of America, United Kingdom of Great Britain and Northern Ireland
- Published
- 4 December 2018
- Authors
- Jacob Menick, Nal Kalchbrenner
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Image generation
- Task
- Image generation
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
- 250M
- Training data
- 251,658,240,000 tokens
250M (Table 4)
batch size: 2048
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
- Google TPU v3
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
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
- Record confidence
- Confident
"state-of-the-art log-likelihoods at 128x128 by a large margin"
Sources
Where this record came from and when it was last checked.
- Reference
- Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling
- Last updated
- 11 February 2026
What the numbers mean
Background
SPN (ImageNet 128) was published by Google Brain,DeepMind, in United States of America, in December 2018. It comes out of industry,Industry.
It works in Image generation, and is recorded as doing image generation.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
How it was trained
It was trained on about 251,658,240,000 tokens of text.
The reason it appears in this catalogue at all is sOTA improvement.
Answers
SPN (ImageNet 128) — common questions
What is SPN (ImageNet 128) used for?
SPN (ImageNet 128) works in Image generation, and is recorded as handling image generation. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run SPN (ImageNet 128)?
None. SPN (ImageNet 128) 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 SPN (ImageNet 128) open source?
No. SPN (ImageNet 128) has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does SPN (ImageNet 128) have?
SPN (ImageNet 128) has 250M parameters. 250M (Table 4). 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 SPN (ImageNet 128)?
SPN (ImageNet 128) was published by Google Brain,DeepMind, based in United States of America, categorised as industry,Industry.
When was SPN (ImageNet 128) released?
SPN (ImageNet 128) was published in December 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.
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.