NMT Transformer 437M
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,Bar-Ilan University
- Organisation type
- Industry,Academia
- Country
- United States of America, Israel
- Published
- 28 February 2019
- Authors
- Roee Aharoni, Melvin Johnson, Orhan Firat
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Translation
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
- 437.7M
- Training data
- tokens
"Regarding the model, for these experiments we use a larger Transformer model with 6 layers in both the encoder and the decoder, model dimension set to 1024, hidden dimension size of 8192, and 16 attention heads. This results in a model with approximately 473.7M parameters."
96M total examples, per Table 4. One sentence per example?
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
- Citations
- 539
"We report results on the publicly available TED talks multilingual corpus where we show that massively multilingual many-to-many models are effective in low resource settings, outperforming the previous state-of-the-art while supporting up to 59 languages."
Sources
Where this record came from and when it was last checked.
- Reference
- Massively Multilingual Neural Machine Translation
- Last updated
- 25 May 2026
What the numbers mean
Background
NMT Transformer 437M was published by Google,Bar-Ilan University, in the country recorded as United States of America, during February 2019. The category the publisher falls under is industry,Academia.
It works in the domain of Language, and is recorded as performing the task of translation.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Training and provenance
Its inclusion criterion: sOTA improvement.
Answers
NMT Transformer 437M — common questions
NMT Transformer 437M— when was it released?
It was published in February 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.
NMT Transformer 437M— what is it used for?
It works in the domain of Language, and is recorded as handling the task of translation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
NMT Transformer 437M— 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.
NMT Transformer 437M— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
NMT Transformer 437M— how many parameters does it have?
It has a parameter count of 437.7M. "Regarding the model, for these experiments we use a larger Transformer model with 6 layers in both the encoder and the decoder, model dimension set to 1024, hidden dimension size of 8192, and 16 attention heads. This results in a model with approximately 473.7M parameters.". 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.
NMT Transformer 437M— who created it?
It was published by Google,Bar-Ilan University, based in United States of America, an organisation categorised as industry,Academia.
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.