Llama 4 Behemoth (preview)

Closed weights Meta AI 2T parameters April 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
Organisation type
Industry
Country
United States of America
Published
5 April 2025

What it does

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

Domain
Multimodal, Language, Vision
Task
Chat, Code generation, Visual question answering, Translation, Language modeling/generation, Quantitative reasoning, Question answering

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
2T

"Llama 4 Behemoth, a 288 billion active parameter model with 16 experts that is our most powerful yet and among the world’s smartest LLMs."

Training data
30,000,000,000,000 tokens

"The overall data mixture for training consisted of more than 30 trillion tokens, which is more than double the Llama 3 pre-training mixture and includes diverse text, image, and video datasets."

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
5.2 × 10²⁵ FLOP

Behemoth's training dataset is at least 30T tokens: https://ai.meta.com/blog/llama-4-multimodal-intelligence/ 6 FLOP / parameter / token * 288 * 10^9 activated parameters * 30 * 10^12 tokens = 5.184e+25 FLOP

How it was established
Operation counting

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 H100 SXM5 80GB
Chips used
32,000
Power draw
43.9 MW
Compute cost
$44,588,964

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

"While we’re not yet releasing Llama 4 Behemoth as it is still training"

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Frontier model
Yes
Likely above 10²³ FLOP
Yes
Why it is tracked
Training cost
Record confidence
Likely

Sources

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

Reference
The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation
Last updated
11 February 2026

What the numbers mean

Where it came from

Llama 4 Behemoth (preview) was published by Meta AI, in United States of America, in April 2025. industry is the category the publisher falls under.

It works in Multimodal, Language, Vision, and is recorded as doing chat, Code generation, Visual question answering, Translation, Language modeling/generation, Quantitative reasoning, Question answering.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Training and provenance

The training run consumed about 5.2 × 10²⁵ FLOP, on NVIDIA H100 SXM5 80GB. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Around 30,000,000,000,000 tokens went into training it.

Its inclusion criterion is training cost.

Answers

Llama 4 Behemoth (preview) — common questions

01

How many parameters does Llama 4 Behemoth (preview) have?

Llama 4 Behemoth (preview) has 2T parameters. "Llama 4 Behemoth, a 288 billion active parameter model with 16 experts that is our most powerful yet and among the world’s smartest LLMs.". 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.

02

Who created Llama 4 Behemoth (preview)?

Llama 4 Behemoth (preview) was published by Meta AI, based in United States of America, categorised as industry.

03

When was Llama 4 Behemoth (preview) released?

Llama 4 Behemoth (preview) was published in April 2025.

04

What is Llama 4 Behemoth (preview) used for?

Llama 4 Behemoth (preview) works in Multimodal, Language, Vision, and is recorded as handling chat, Code generation, Visual question answering, Translation, Language modeling/generation, Quantitative reasoning, Question answering. 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.

05

How much compute was used to train Llama 4 Behemoth (preview)?

Around 5.2 × 10²⁵ FLOP, on 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.

06

What GPU do I need to run Llama 4 Behemoth (preview)?

None. Llama 4 Behemoth (preview) 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.

07

Is Llama 4 Behemoth (preview) open source?

No. Llama 4 Behemoth (preview) has not had its weights published, so it exists only as a service controlled by its owner.

Source

Original publication

Record last updated 11 February 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.