Brain2Qwerty

Closed weights Meta AI,Universite de Technologie de Compiègne – CNRS,Basque Center on Cognition 400M parameters February 2025

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
Meta AI,Universite de Technologie de Compiègne – CNRS,Basque Center on Cognition
Organisation type
Industry,Academia,Academia
Country
United States of America, France, Spain
Published
18 February 2025
Authors
Jarod Lévy,, Mingfang (Lucy) Zhang, Svetlana Pinet, Jérémy Rapin, Hubert Banville, Stéphane d’Ascoli, Jean-Rémi King

What it does

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

Domain
Language
Task
Language generation

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
400M

a total of ∼ 400M parameters (258M for Conv, 138M for Trans)

Training data
tokens

The model is trained for 100 epochs with a batch size of 128 Custom dataset collected from 35 participants typing 128 unique Spanish sentences

Epochs
100

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
1.6 × 10¹⁸ FLOP

125000000000000 FLOP / GPU / sec [V100 reported, bf16 assumed] * 1 GPU * 12 hours * 3600 sec / hour * 0.3 [assumed utilization] = 1.62e+18 FLOP

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 V100
Chips used
1
Wall-clock time
12 hours

Training was conducted on a single NVIDIA Tesla V100 Volta GPU with 32 GB of memory. The total runtime for training one model is ∼12 hours

Power draw
324 W

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
Unreleased

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
Brain-to-Text Decoding: A Non-invasive Approach via Typing
Last updated
28 November 2025

What the numbers mean

Where it came from

Brain2Qwerty was published by Meta AI,Universite de Technologie de Compiègne – CNRS,Basque Center on Cognition, in the country recorded as United States of America, during February 2025. The category the publisher falls under is industry,Academia,Academia.

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

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

How it was trained

Producing it required arithmetic totalling around 1.6 × 10¹⁸ FLOP, on hardware recorded as NVIDIA V100. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Answers

Brain2Qwerty — common questions

01

Brain2Qwerty— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language generation. 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.

02

Brain2Qwerty— how much compute was used to train it?

Training consumed around 1.6 × 10¹⁸ FLOP, on hardware recorded as NVIDIA V100. 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

Brain2Qwerty— 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

Brain2Qwerty— is it open source?

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

05

Brain2Qwerty— how many parameters does it have?

It has a parameter count of 400M. a total of ∼ 400M parameters (258M for Conv, 138M for Trans). 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.

06

Brain2Qwerty— who created it?

It was published by Meta AI,Universite de Technologie de Compiègne – CNRS,Basque Center on Cognition, based in United States of America, an organisation categorised as industry,Academia,Academia.

07

Brain2Qwerty— when was it released?

It was published in February 2025.

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.