Grok 4

Closed weights xAI 3T parameters July 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
xAI
Organisation type
Industry
Country
United States of America
Published
9 July 2025

What it does

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

Domain
Language, Multimodal, Vision
Task
Language modeling/generation, Question answering, Search, Visual question answering, Character recognition (OCR), Image captioning, Quantitative reasoning

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
3T

Rumored to be 2.4T params (https://x.com/kalomaze/status/1942996555088134592)

Training data
tokens

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 × 10²⁶ FLOP

We think that RL relative to pre-compute is between our estimate for o3 (10% of pre-training) and the 100% implied by this slide in the launch ( https://archive.is/f0vJU ). Assuming the same pre-training as Grok 3 (also implied by that slide, and much more consistent) and that Grok 3 used a tenth as much RL, we get: 2 * (grok3/1.1) in the high case (rl is 10% of grok 3, so grok3/1.1 is grok3 precompute, and in this case twice that is grok 4) 1.1 * (grok3/1.01) in the low case The geometric mean…

How it was established
Comparison with other models

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Chips used
200,000
Compute cost
$387,842,678
Data centre
"we utilized Colossus, our 200,000 GPU cluster, to run reinforcement learning training that refines Grok's reasoning abilities at pretraining scale"

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
Training code
Unreleased

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
Speculative

Sources

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

Reference
Grok 4
Last updated
11 February 2026

What the numbers mean

Where it came from

Grok 4 was published by xAI, in United States of America, in July 2025. industry is the category the publisher falls under.

It works in Language, Multimodal, Vision, and is recorded as doing language modeling/generation, Question answering, Search, Visual question answering, Character recognition (OCR), Image captioning, Quantitative reasoning.

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

How it was trained

Training it took roughly 5 × 10²⁶ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

The reason it appears in this catalogue at all is training cost.

Answers

Grok 4 — common questions

01

What GPU do I need to run Grok 4?

None. Grok 4 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.

02

Is Grok 4 open source?

No. Grok 4 has not had its weights published, so it exists only as a service controlled by its owner.

03

How many parameters does Grok 4 have?

Grok 4 has 3T parameters. Rumored to be 2.4T params (https://x.com/kalomaze/status/1942996555088134592). 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.

04

Who created Grok 4?

Grok 4 was published by xAI, based in United States of America, categorised as industry.

05

When was Grok 4 released?

Grok 4 was published in July 2025.

06

What is Grok 4 used for?

Grok 4 works in Language, Multimodal, Vision, and is recorded as handling language modeling/generation, Question answering, Search, Visual question answering, Character recognition (OCR), Image captioning, Quantitative reasoning. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

07

How much compute was used to train Grok 4?

Around 5 × 10²⁶ FLOP. 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.

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.