ELMo

Closed weights University of Washington,Allen Institute for AI 94M parameters February 2018

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
University of Washington,Allen Institute for AI
Organisation type
Academia,Research collective
Country
United States of America
Published
1 February 2018
Authors
Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke Zettlemoyer

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Language
Task
Question answering, Sentiment classification, Language modeling
Approach
Self-supervised learning

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
94M
Training data
2,000,000,000 tokens

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
3.3 × 10¹⁵ FLOP

3300e12 - https://github.com/amirgholami/ai_and_memory_wall

How it was established
Third-party estimation

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
Speculative
Citations
12,156

Sources

Where this record came from and when it was last checked.

Reference
Deep contextualized word representations
Last updated
25 May 2026

What the numbers mean

Background

ELMo was published by University of Washington,Allen Institute for AI, in United States of America, in February 2018. academia,Research collective is the category the publisher falls under.

It works in Language, and is recorded as doing question answering, Sentiment classification, Language modeling.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

Producing it required around 3.3 × 10¹⁵ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

The training set ran to roughly 2,000,000,000 tokens.

The reason it appears in this catalogue at all is highly cited.

Answers

ELMo — common questions

01

What GPU do I need to run ELMo?

None. ELMo 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.

02

Is ELMo open source?

The licensing for ELMo was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

03

How many parameters does ELMo have?

ELMo has 94M parameters. 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.

04

Who created ELMo?

ELMo was published by University of Washington,Allen Institute for AI, based in United States of America, categorised as academia,Research collective.

05

When was ELMo released?

ELMo was published in February 2018. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

What is ELMo used for?

ELMo works in Language, and is recorded as handling question answering, Sentiment classification, Language modeling. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

07

How much compute was used to train ELMo?

Around 3.3 × 10¹⁵ 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.

Source

Original publication

Record last updated 25 May 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.