KN5 LM + RNN 400/10 (WSJ)
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
- Brno University of Technology,Johns Hopkins University
- Organisation type
- Academia,Academia
- Country
- Czechia, United States of America
- Published
- 26 September 2010
- Authors
- T. Mikolov, M. Karafiat, L. Burget, J. Cernock ´ y, and S. Khudanpur
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Speech
- Task
- Transcription
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
- 22.2M
- Training data
- 6,400,000 tokens
RNN 400/10 indicates that the model has 400 units in the hidden layer and merges words that occur less than 10 times in the training set. The model is trained on a 6.4M word subset of the NYT subset of English Gigaword. In this colab notebook, I estimate the vocabulary after merging infrequent words using english word frequency data at around 27.5k: https://colab.research.google.com/drive/1K5qH0EqXtFwTLESNtp4oelCM28GpGXt6?usp=sharing Then RNN 400/10 has: (27.5k + 400) * 400 + (400 * 27.5k) = 2…
The training corpus consists of 37M words from NYT section of English Gigaword. As it is very time consuming to train RNN LM on large data, we have used only up to 6.4M words for training RNN models (300K sentences) - it takes several weeks to train the most complex models
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
- 1.7 × 10¹⁶ FLOP
- How it was established
- Operation counting
"Convergence is usually achieved after 10-20 epochs." 6 * 22,160,000 * 20 * 6.4M = 1.70e16
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
- 504 hours (21 days)
"it takes several weeks to train the most complex models" Assume several weeks is around 3 weeks, or 504 hours
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Frontier model
- Yes
- Why it is tracked
- Highly cited
- Record confidence
- Confident
- Citations
- 6,038
Sources
Where this record came from and when it was last checked.
- Reference
- Recurrent neural network based language model
- Last updated
- 11 February 2026
What the numbers mean
Where it came from
KN5 LM + RNN 400/10 (WSJ) was published by Brno University of Technology,Johns Hopkins University, in the country recorded as Czechia, during September 2010. The category the publisher falls under is academia,Academia.
It works in the domain of Speech, and is recorded as performing the task of transcription.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Training and provenance
Training it took a computation budget of roughly 1.7 × 10¹⁶ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 6,400,000 tokens of text.
Its inclusion criterion: highly cited.
Answers
KN5 LM + RNN 400/10 (WSJ) — common questions
KN5 LM + RNN 400/10 (WSJ)— who created it?
It was published by Brno University of Technology,Johns Hopkins University, based in Czechia, an organisation categorised as academia,Academia.
KN5 LM + RNN 400/10 (WSJ)— when was it released?
It was published in September 2010. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
KN5 LM + RNN 400/10 (WSJ)— what is it used for?
It works in the domain of Speech, and is recorded as handling the task of transcription. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
KN5 LM + RNN 400/10 (WSJ)— how much compute was used to train it?
Training consumed around 1.7 × 10¹⁶ 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.
KN5 LM + RNN 400/10 (WSJ)— 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.
KN5 LM + RNN 400/10 (WSJ)— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
KN5 LM + RNN 400/10 (WSJ)— how many parameters does it have?
It has a parameter count of 22.2M. RNN 400/10 indicates that the model has 400 units in the hidden layer and merges words that occur less than 10 times in the training set. The model is trained on a 6.4M word subset of the NYT subset of English Gigaword. In this colab notebook, I estimate the vocabulary after merging infrequent words using english word frequency data at around 27.5k: https://colab.research.google.com/drive/1K5qH0EqXtFwTLESNtp4oelCM28GpGXt6?usp=sharing Then RNN 400/10 has: (27.5k + 400) * 400 + (400 * 27.5k) = 22.16M parameters The KN5 LM is effectively a lookup table over 5-grams in it's training data. In one sense, this means it has approximately as many parameters as unique 5-grams in the 37M words of training data. However, these aren't parameters in the same sense as neural networks, as they are accessed as a lookup table, so on each forward pass only one parameter is active. I choose not to include these parameters in our count. 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.