KN5 LM + RNN 400/10 (WSJ)

Closed weights Brno University of Technology,Johns Hopkins University 22.2M parameters September 2010

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

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…

Training data
6,400,000 tokens

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

"Convergence is usually achieved after 10-20 epochs." 6 * 22,160,000 * 20 * 6.4M = 1.70e16

How it was established
Operation counting

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 Czechia, in September 2010. academia,Academia is the category the publisher falls under.

It works in Speech, and is recorded as doing 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 roughly 1.7 × 10¹⁶ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

The training set ran to roughly 6,400,000 tokens.

Its inclusion criterion is highly cited.

Answers

KN5 LM + RNN 400/10 (WSJ) — common questions

01

Who created KN5 LM + RNN 400/10 (WSJ)?

KN5 LM + RNN 400/10 (WSJ) was published by Brno University of Technology,Johns Hopkins University, based in Czechia, categorised as academia,Academia.

02

When was KN5 LM + RNN 400/10 (WSJ) released?

KN5 LM + RNN 400/10 (WSJ) 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.

03

What is KN5 LM + RNN 400/10 (WSJ) used for?

KN5 LM + RNN 400/10 (WSJ) works in Speech, and is recorded as handling transcription. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

04

How much compute was used to train KN5 LM + RNN 400/10 (WSJ)?

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.

05

What GPU do I need to run KN5 LM + RNN 400/10 (WSJ)?

None. KN5 LM + RNN 400/10 (WSJ) 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.

06

Is KN5 LM + RNN 400/10 (WSJ) open source?

The licensing for KN5 LM + RNN 400/10 (WSJ) was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

07

How many parameters does KN5 LM + RNN 400/10 (WSJ) have?

KN5 LM + RNN 400/10 (WSJ) has 22.2M parameters. 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.

Source

Original publication

Record last updated 11 February 2026

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.