Multi-Token Prediction 13B

Closed weights Facebook AI Research 13B parameters April 2024

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
Facebook AI Research
Organisation type
Industry
Country
United States of America, France
Published
30 April 2024
Authors
Fabian Gloeckle, Badr Youbi Idrissi, Baptiste Rozière, David Lopez-Paz, Gabriel Synnaeve

What it does

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

Domain
Language
Task
Code 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
13B

13B (Figure 1)

Training data
tokens

209.7B (Table S13)

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
1.5 × 10²³ FLOP

"training all models reported in the paper required around 500K GPU hours of computation on hardware of type A100-80GB and H100." A100-80 GB peak FLOP/s [assumed fp16 precision]: 77970000000000 H100 peak FLOP/s [assumed SXM5 TensorCore]: 989000000000000 assuming 50/50 usage: (77970000000000+989000000000000)*0.5*500000hours*3600s*0.3=2.880819e+23 for ALL models in the paper assuming this model has taken around 16% of all used compute (https://docs.google.com/spreadsheets/d/1Yc-HAdYgn6e9SUIliMaQ…

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 A100 SXM4 80 GB,NVIDIA H100 SXM5 80GB

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.

Likely above 10²³ FLOP
Yes
Record confidence
Likely

Sources

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

Reference
Better & Faster Large Language Models via Multi-token Prediction
Last updated
28 November 2025

What the numbers mean

Where it came from

Multi-Token Prediction 13B was published by Facebook AI Research, in United States of America, in April 2024. industry is the category the publisher falls under.

It works in Language, and is recorded as doing code generation.

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

What went into building it

Training it took roughly 1.5 × 10²³ FLOP of computation, on NVIDIA A100 SXM4 80 GB,NVIDIA H100 SXM5 80GB — a measure of what producing the model cost, not of how fast it answers.

Answers

Multi-Token Prediction 13B — common questions

01

How much compute was used to train Multi-Token Prediction 13B?

Around 1.5 × 10²³ FLOP, on NVIDIA A100 SXM4 80 GB,NVIDIA H100 SXM5 80GB. 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.

02

What GPU do I need to run Multi-Token Prediction 13B?

None. Multi-Token Prediction 13B 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.

03

Is Multi-Token Prediction 13B open source?

No. Multi-Token Prediction 13B has not had its weights published, so it exists only as a service controlled by its owner.

04

How many parameters does Multi-Token Prediction 13B have?

Multi-Token Prediction 13B has 13B parameters. 13B (Figure 1). 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.

05

Who created Multi-Token Prediction 13B?

Multi-Token Prediction 13B was published by Facebook AI Research, based in United States of America, categorised as industry.

06

When was Multi-Token Prediction 13B released?

Multi-Token Prediction 13B was published in April 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.

07

What is Multi-Token Prediction 13B used for?

Multi-Token Prediction 13B works in Language, and is recorded as handling code generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

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.