xLSTM 1.4B
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
- Johannes Kepler University Linz
- Organisation type
- Academia
- Country
- Austria
- Published
- 7 May 2024
- Authors
- Maximilian Beck, Korbinian Pöppel, Markus Spanring, Andreas Auer, Oleksandra Prudnikova, Michael Kopp, Günter Klambauer, Johannes Brandstetter, Sepp Hochreiter
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
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
- 1.4B
- Training data
- tokens
- Epochs
- 1
"We therefore increase the amount of training data and train on 300B tokens from SlimPajama. "
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
"We developed and trained all our models and baselines over the course of three months on a cluster with 128 nodes of eight NVIDIA A100 GPUs each." 1024 6*300000000*1422600000=2.56068e+18
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 A100
- Chips used
- 1,024
- Power draw
- 809.3 kW
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- xLSTM: Extended Long Short-Term Memory
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
xLSTM 1.4B was published by Johannes Kepler University Linz, in Austria, in May 2024. academia is the category the publisher falls under.
It works in Language.
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 2.6 × 10¹⁸ FLOP, on NVIDIA A100. That figure describes the cost of creating it and has no bearing on how quickly it generates text.
Answers
xLSTM 1.4B — common questions
What GPU do I need to run xLSTM 1.4B?
None. xLSTM 1.4B 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 xLSTM 1.4B open source?
The licensing for xLSTM 1.4B 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 xLSTM 1.4B have?
xLSTM 1.4B has 1.4B 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.
Who created xLSTM 1.4B?
xLSTM 1.4B was published by Johannes Kepler University Linz, based in Austria, categorised as academia.
When was xLSTM 1.4B released?
xLSTM 1.4B was published in May 2024. 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 xLSTM 1.4B used for?
xLSTM 1.4B works in Language. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train xLSTM 1.4B?
Around 2.6 × 10¹⁸ FLOP, on NVIDIA A100. 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.
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.