VD-LSTM+REAL Small
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
- Stanford University,Salesforce Research
- Organisation type
- Academia,Industry
- Country
- United States of America
- Published
- 4 November 2016
- Authors
- Hakan Inan, Khashayar Khosravi, Richard Socher
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.
- Parameters
- 6.8M
- Training data
- tokens
- Epochs
- 60
VD-LSTM+REAL Large has 51M parameters. The parameter count of the Small model is not reported, but they say it has 200 hidden units per layer, compared to 1500 for the Large model. Neglecting the rest of the architecture, 51M * (200/1500) = 6.8M
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.
- Record confidence
- Likely
- Citations
- 404
- Benchmark data
- VD-LSTM+REAL Small
Sources
Where this record came from and when it was last checked.
- Reference
- Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
VD-LSTM+REAL Small was published by Stanford University,Salesforce Research, in United States of America, in November 2016. academia,Industry is the category the publisher falls under.
It works in Language, and is recorded as doing language modeling.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Answers
VD-LSTM+REAL Small — common questions
Who created VD-LSTM+REAL Small?
VD-LSTM+REAL Small was published by Stanford University,Salesforce Research, based in United States of America, categorised as academia,Industry.
When was VD-LSTM+REAL Small released?
VD-LSTM+REAL Small was published in November 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.
What is VD-LSTM+REAL Small used for?
VD-LSTM+REAL Small works in Language, and is recorded as handling language modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
What GPU do I need to run VD-LSTM+REAL Small?
None. VD-LSTM+REAL Small 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 VD-LSTM+REAL Small open source?
No. VD-LSTM+REAL Small has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does VD-LSTM+REAL Small have?
VD-LSTM+REAL Small has 6.8M parameters. VD-LSTM+REAL Large has 51M parameters. The parameter count of the Small model is not reported, but they say it has 200 hidden units per layer, compared to 1500 for the Large model. Neglecting the rest of the architecture, 51M * (200/1500) = 6.8M. 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.
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.