PAGnol-XL

Closed weights LightOn,Laboratoire de Physique de l'Ecole Normale (LPENS),INRIA 1.5B parameters October 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
LightOn,Laboratoire de Physique de l'Ecole Normale (LPENS),INRIA
Organisation type
Industry,Academia,Academia
Country
France
Published
16 October 2021
Authors
Julien Launay, E.L. Tommasone, Baptiste Pannier, François Boniface, Amélie Chatelain, Alessandro Cappelli, Iacopo Poli, Djamé Seddah

What it does

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

Domain
Language
Task
Language modeling, Language modeling/generation, Translation
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
1.5B
Training data
tokens

Section 4.1: 32G tokens => 32e9*0.75 = 24e9 words

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 × 10²⁰ FLOP

They report their compute directly. From section 8: "About 62k GPU-hours on the Jean Zay HPC Cluster." Jean Zay uses both A100 and V100 GPUs, and maybe other stuff as well? Note they explicitly call out V100 in their Appendix A. https://www.hpcwire.com/2021/11/17/frances-jean-zay-supercomputer-gets-ai-boost-from-hpe-nvidia/

How it was established
Reported

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 Tesla V100 SXM2

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
API access

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
10

Sources

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

Reference
PAGnol: An Extra-Large French Generative Model
Last updated
25 May 2026

What the numbers mean

Background

PAGnol-XL was published by LightOn,Laboratoire de Physique de l'Ecole Normale (LPENS),INRIA, in France, in October 2021. The organisation is categorised as industry,Academia,Academia.

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

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

Training and provenance

The training run consumed about 2.6 × 10²⁰ FLOP, on NVIDIA Tesla V100 SXM2. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Answers

PAGnol-XL — common questions

01

When was PAGnol-XL released?

PAGnol-XL was published in October 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.

02

What is PAGnol-XL used for?

PAGnol-XL works in Language, and is recorded as handling language modeling, Language modeling/generation, Translation. 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.

03

How much compute was used to train PAGnol-XL?

Around 2.6 × 10²⁰ FLOP, on NVIDIA Tesla V100 SXM2. 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.

04

What GPU do I need to run PAGnol-XL?

None. PAGnol-XL 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.

05

Is PAGnol-XL open source?

No. PAGnol-XL has not had its weights published, so it exists only as a service controlled by its owner.

06

How many parameters does PAGnol-XL have?

PAGnol-XL has 1.5B 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.

07

Who created PAGnol-XL?

PAGnol-XL was published by LightOn,Laboratoire de Physique de l'Ecole Normale (LPENS),INRIA, based in France, categorised as industry,Academia,Academia.

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.