Local Transformer (WT103)
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 Research
- Organisation type
- Industry
- Country
- United States of America
- Published
- 12 March 2020
- Authors
- Aurko Roy, Mohammad Saffar, Ashish Vaswani, David Grangier
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling
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.
- Training data
- 103,000,000 tokens
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
- Chips used
- 64
- Power draw
- 58.9 kW
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 source
code (Apache): https://github.com/google-research/google-research/blob/master/routing_transformer/problems/wikitext103.py
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
- 754
- Benchmark data
- Local Transformer
Sources
Where this record came from and when it was last checked.
- Reference
- Efficient Content-Based Sparse Attention with Routing Transformers
- Last updated
- 25 May 2026
What the numbers mean
About this model
Local Transformer (WT103) was published by Google Research, in the country recorded as United States of America, during March 2020. It comes out of an organisation categorised as industry.
It works in the domain of Language, and is recorded as performing the task of language modeling.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
Training consumed a corpus of around 103,000,000 tokens of text.
Answers
Local Transformer (WT103) — common questions
Local Transformer (WT103)— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
Local Transformer (WT103)— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
Local Transformer (WT103)— who created it?
It was published by Google Research, based in United States of America, an organisation categorised as industry.
Local Transformer (WT103)— when was it released?
It was published in March 2020. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Local Transformer (WT103)— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
Local Transformer (WT103)— 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.
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.