KN-LM
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
- Organisation type
- Industry
- Country
- United States of America
- Published
- 22 June 2007
- Authors
- T. Brants, Ashok Popat, P. Xu, F. Och, J. Dean
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
- 21B
- Training data
- 31,000,000,000 tokens
Table 2
Table 2
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
- 7.7 × 10¹⁷ FLOP
- How it was established
- Hardware
Trained for 2 days on 400 machines (Table 2) Assuming a Nehalem based processor with 8 FLOP/cycle (https://www.agner.org/optimize/microarchitecture.pdf#page=105.06) , 2 cores and 2.33 GHz clock speed: 8*2*2330000000=37280000000 FLOP/s Compute: 400*37280000000*2*24*60*60*0.3=773038080000000000=7.7e17
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Chips used
- 400
- Wall-clock time
- 48 hours
Table 2
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
- Training cost,Highly cited
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- Large Language Models in Machine Translation
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
KN-LM was published by Google, in United States of America, in June 2007. It comes out of industry.
It works in Language, and is recorded as doing language modeling.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
The training run consumed about 7.7 × 10¹⁷ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
Around 31,000,000,000 tokens went into training it.
It is tracked in the underlying dataset for one reason in particular: training cost,Highly cited.
Answers
KN-LM — common questions
Who created KN-LM?
KN-LM was published by Google, based in United States of America, categorised as industry.
When was KN-LM released?
KN-LM was published in June 2007. 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 KN-LM used for?
KN-LM 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.
How much compute was used to train KN-LM?
Around 7.7 × 10¹⁷ 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.
What GPU do I need to run KN-LM?
None. KN-LM 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 KN-LM open source?
The licensing for KN-LM was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does KN-LM have?
KN-LM has 21B parameters. Table 2. 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.