Latent semantic analysis
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
- University of Chicago,Bell Laboratories,University of Western Ontario
- Organisation type
- Academia,Industry,Academia
- Country
- United States of America, Canada
- Published
- 5 April 1988
- Authors
- Scott Deerwester, Susan T. Dumais, George W. Furnas, Thomas K. Landauer, Richard Harshman
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Semantic embedding, Document representation, Language Structure Modeling, Search
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
- tokens
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
- Historical significance
- Record confidence
- Unknown
Might be the first model that used word embeddings
Sources
Where this record came from and when it was last checked.
- Reference
- Indexing by latent semantic analysis
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Latent semantic analysis was published by University of Chicago,Bell Laboratories,University of Western Ontario, in United States of America, in April 1988. academia,Industry,Academia is the category the publisher falls under.
It works in Language, and is recorded as doing semantic embedding, Document representation, Language Structure Modeling, Search.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
Its inclusion criterion is historical significance.
Answers
Latent semantic analysis — common questions
How many parameters does Latent semantic analysis have?
No parameter count has been published for Latent semantic analysis, which is why no memory or speed figure appears on this page.
Who created Latent semantic analysis?
Latent semantic analysis was published by University of Chicago,Bell Laboratories,University of Western Ontario, based in United States of America, categorised as academia,Industry,Academia.
When was Latent semantic analysis released?
Latent semantic analysis was published in April 1988. 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 Latent semantic analysis used for?
Latent semantic analysis works in Language, and is recorded as handling semantic embedding, Document representation, Language Structure Modeling, Search. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run Latent semantic analysis?
None. Latent semantic analysis 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 Latent semantic analysis open source?
No. Latent semantic analysis has not had its weights published, so it exists only as a service controlled by its owner.
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.