DistBelief NNLM
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
- 16 January 2013
- Authors
- Tomas Mikolov, Kai Chen, G. Corrado, J. Dean
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Semantic embedding
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
- 6,000,000,000 tokens
Largest system is trained on 6B words (Table 6)
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
- 2.6 × 10¹⁸ FLOP
- How it was established
- Hardware
Trained for 14 days on 180 CPU cores (Table 6) Roughly estimating the performance of CPUs in a HPC around 2013: 16 FP32 operations per cycle, 2.5GHz, 0.3 utilization Time: 14*24*60*60=1209600s FLOPs: 0.3*180*16*2500000000=2160000000000 Training compute: 1209600s * 2160000000000 = 2612736000000000000 = 2.61e18 https://www.wolframalpha.com/input?i=16+FLOP+*+2.5+GHz+*+180+*+14+days+*+0.3
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
- 180
- Wall-clock time
- 336 hours (14 days)
- Compute cost
- $3,255
Trained for 14 days (Table 6)
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,SOTA improvement
- Record confidence
- Likely
- Citations
- 41,000
they seem to use their own evaluation protocol, I don't see any standard benchmarks
Sources
Where this record came from and when it was last checked.
- Reference
- Efficient Estimation of Word Representations in Vector Space
- Last updated
- 28 November 2025
What the numbers mean
About this model
DistBelief NNLM was published by Google, in United States of America, in January 2013. industry is the category the publisher falls under.
It works in Language, and is recorded as doing semantic embedding.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
Producing it required around 2.6 × 10¹⁸ FLOP of arithmetic, which is a statement about the training budget rather than about inference.
It was trained on about 6,000,000,000 tokens of text.
Its inclusion criterion is highly cited,SOTA improvement.
Answers
DistBelief NNLM — common questions
Is DistBelief NNLM open source?
The licensing for DistBelief NNLM 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 DistBelief NNLM have?
No parameter count has been published for DistBelief NNLM, which is why no memory or speed figure appears on this page.
Who created DistBelief NNLM?
DistBelief NNLM was published by Google, based in United States of America, categorised as industry.
When was DistBelief NNLM released?
DistBelief NNLM was published in January 2013. 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 DistBelief NNLM used for?
DistBelief NNLM works in Language, and is recorded as handling semantic embedding. These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train DistBelief NNLM?
Around 2.6 × 10¹⁸ 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 DistBelief NNLM?
None. DistBelief NNLM 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.
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.