Transformer-XL + PowerSGD + L-Greco

Closed weights Institute of Science and Technology Austria (ISTA),Neural Magic October 2022

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
Institute of Science and Technology Austria (ISTA),Neural Magic
Organisation type
Academia,Industry
Country
Austria, United States of America
Published
31 October 2022
Authors
Mohammadreza Alimohammadi, Ilia Markov, Elias Frantar, Dan Alistarh

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.

Training data
103,000,000 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
1.3 × 10¹⁸ FLOP

35580000000000 FLOP / sec [fp16 precision assumed] * 15400 sec [see training time notes] * 8 GPUs * 0.3 [assumed utilization] = 1.3150368e+18 FLOP _______ They used similar estimation (4.14 × 10^17 FLOP) in the Algorithmic Progress paper - not sure how exactly it was calculated

How it was established
Hardware

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA GeForce RTX 3090
Chips used
8
Wall-clock time
4 hours

40k steps [table 7] * 0.385 sec/step [figure 3] = 15400 sec = 4.28 hours

Power draw
5.6 kW

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

Apache 2. looks like just code: https://github.com/LGrCo/L-GreCo/tree/master/Transformer-XL

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
4
Benchmark data
Transformer-XL + PowerSGD + L-Greco

Sources

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

Reference
L-GreCo: An Efficient and General Framework for Layerwise-Adaptive Gradient Compression
Last updated
28 November 2025

What the numbers mean

About this model

Transformer-XL + PowerSGD + L-Greco was published by Institute of Science and Technology Austria (ISTA),Neural Magic, in the country recorded as Austria, during October 2022. It comes out of an organisation categorised as academia,Industry.

It works in the domain of Language, and is recorded as performing the task of language modeling.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

How it was trained

The training run consumed about 1.3 × 10¹⁸ FLOP, on hardware recorded as NVIDIA GeForce RTX 3090. That figure measures what producing the model cost, and has no bearing on how fast it answers.

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

Answers

Transformer-XL + PowerSGD + L-Greco — common questions

01

Transformer-XL + PowerSGD + L-Greco— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling. These are the areas it was designed around; they describe intent rather than a hard boundary.

02

Transformer-XL + PowerSGD + L-Greco— how much compute was used to train it?

Training consumed around 1.3 × 10¹⁸ FLOP, on hardware recorded as NVIDIA GeForce RTX 3090. 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.

03

Transformer-XL + PowerSGD + L-Greco— what GPU do I need to run it?

None. This 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.

04

Transformer-XL + PowerSGD + L-Greco— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

05

Transformer-XL + PowerSGD + L-Greco— how many parameters does it have?

No parameter count has been published for it, which is why no memory or speed figure appears on this page.

06

Transformer-XL + PowerSGD + L-Greco— who created it?

It was published by Institute of Science and Technology Austria (ISTA),Neural Magic, based in Austria, an organisation categorised as academia,Industry.

07

Transformer-XL + PowerSGD + L-Greco— when was it released?

It was published in October 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

Source

Original publication

Record last updated 28 November 2025

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.