Linear Transformer (large)

Closed weights IDSIA 90M parameters February 2021

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
IDSIA
Organisation type
Academia
Country
Switzerland
Published
22 February 2021
Authors
Imanol Schlag, Kazuki Irie, Jürgen Schmidhuber

What it does

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

Domain
Language
Task
Language modeling, Translation

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
90M

90M (medium)

Training data
103,000,000 tokens

batch size: 56 sequences 70 epochs target segment lengths of 384

Epochs
70

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
3.9 × 10¹⁸ FLOP

6 FLOP / token / parameter * 90000000 parameters * 103000000 tokens * 70 epochs = 3.8934e+18 FLOP

How it was established
Operation counting

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Open source

code, Apache license: https://github.com/IDSIA/lmtool-fwp/tree/master/example_scripts/2021_linear_transformers_are_secretly_fwps

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Confident
Citations
405
Benchmark data
Linear Transformer (large)

Sources

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

Reference
Linear Transformers Are Secretly Fast Weight Programmers
Last updated
25 May 2026

What the numbers mean

Background

Linear Transformer (large) was published by IDSIA, in Switzerland, in February 2021. academia is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling, Translation.

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

The training run consumed about 3.9 × 10¹⁸ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

The training set ran to roughly 103,000,000 tokens.

Answers

Linear Transformer (large) — common questions

01

How many parameters does Linear Transformer (large) have?

Linear Transformer (large) has 90M parameters. 90M (medium). 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.

02

Who created Linear Transformer (large)?

Linear Transformer (large) was published by IDSIA, based in Switzerland, categorised as academia.

03

When was Linear Transformer (large) released?

Linear Transformer (large) was published in February 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

What is Linear Transformer (large) used for?

Linear Transformer (large) works in Language, and is recorded as handling language modeling, Translation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

05

How much compute was used to train Linear Transformer (large)?

Around 3.9 × 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.

06

What GPU do I need to run Linear Transformer (large)?

None. Linear Transformer (large) 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.

07

Is Linear Transformer (large) open source?

No. Linear Transformer (large) has not had its weights published, so it exists only as a service controlled by its owner.

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.