RankNet
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
- Microsoft Research,Microsoft
- Organisation type
- Industry,Industry
- Country
- United States of America
- Published
- 7 August 2005
- Authors
- Chris Burges, Tal Shaked, Erin Renshaw, Ari Lazier, Matt Deeds, Nicole Hamilton, Greg HullenderAuthors Info & Claims
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Search
- Task
- 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.
- Parameters
- 5.7K
- Training data
- 3,464,289 tokens
- Epochs
- 22
Model is "a two layer net with 10 hidden units" Input is of size 569 "In all, we use 569 features" Parameters: 569*10 + 10 for hidden layer 10*1 + 1 for output layer
"This resulted in our training on 384,314 query/document feature vectors, and on 3,464,289 pairs."
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 3.5 × 10¹² FLOP
- How it was established
- Operation counting
FLOPs per forward pass: 2*parameters = 11422 FLOPs per pair (data point): two forward passes and one backward pass ("A forward prop is performed for the first sample; each node’s activation and gradient value are stored; a forward prop is then performed for the second sample, and the activations and gradients are again stored. The gradient of the cost is then *formula*") = 2*11422 + 2*11422 = 45688 Total FLOPs = (FLOPs per pair = 45688)*(pairs = 3,464,289)*(epochs = 22) = 3.48E12
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Wall-clock time
- 6 hours
Table 6
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
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
- Highly cited
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Learning to rank using gradient descent
- Last updated
- 28 November 2025
What the numbers mean
Background
RankNet was published by Microsoft Research,Microsoft, in the country recorded as United States of America, during August 2005. The category the publisher falls under is industry,Industry.
It works in the domain of Search, and is recorded as performing the task of search.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
How it was trained
The training run consumed about 3.5 × 10¹² FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 3,464,289 tokens of text.
Its inclusion criterion: highly cited.
Answers
RankNet — common questions
RankNet— 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.
RankNet— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
RankNet— how many parameters does it have?
It has a parameter count of 5.7K. Model is "a two layer net with 10 hidden units" Input is of size 569 "In all, we use 569 features" Parameters: 569*10 + 10 for hidden layer 10*1 + 1 for output layer. 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.
RankNet— who created it?
It was published by Microsoft Research,Microsoft, based in United States of America, an organisation categorised as industry,Industry.
RankNet— when was it released?
It was published in August 2005. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
RankNet— what is it used for?
It works in the domain of Search, and is recorded as handling the task of search. These are the areas it was designed around; they describe intent rather than a hard boundary.
RankNet— how much compute was used to train it?
Training consumed around 3.5 × 10¹² FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
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.