Hawk

Closed weights Google DeepMind 7B parameters February 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
Google DeepMind
Organisation type
Industry
Country
United States of America
Published
29 February 2024
Authors
Soham De, Samuel L. Smith, Anushan Fernando, Aleksandar Botev, George Cristian-Muraru, Albert Gu, Ruba Haroun, Leonard Berrada, Yutian Chen, Srivatsan Srinivasan, Guillaume Desjardins, Arnaud Doucet, David Budden, Yee Whye Teh, Razvan Pascanu, Nando De Freitas, Caglar Gulcehre

What it does

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

Domain
Language
Task
Language modeling/generation, Chat

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
7B

"All three model families are trained at a range of model scales from 100M to 7B parameters, with an additional Griffin model with 14 billion parameters."

Training data
300,000,000,000 tokens

Table 1

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
4 × 10²¹ FLOP

Figure 1.a Digitized and found 3.95e21 for biggest Hawk model

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
Google TPU v3

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
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Last updated
28 November 2025

What the numbers mean

About this model

Hawk was published by Google DeepMind, in the country recorded as United States of America, during February 2024. It comes out of an organisation categorised as industry.

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

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 4 × 10²¹ FLOP, on hardware recorded as Google TPU v3. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of about 300,000,000,000 tokens of text.

Answers

Hawk — common questions

01

Hawk— how much compute was used to train it?

Training consumed around 4 × 10²¹ FLOP, on hardware recorded as Google TPU v3. 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

Hawk— 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.

03

Hawk— is it open source?

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

04

Hawk— how many parameters does it have?

It has a parameter count of 7B. "All three model families are trained at a range of model scales from 100M to 7B parameters, with an additional Griffin model with 14 billion 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.

05

Hawk— who created it?

It was published by Google DeepMind, based in United States of America, an organisation categorised as industry.

06

Hawk— when was it released?

It was published in February 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

Hawk— what is it used for?

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