ALLaM adapted 70B

Closed weights Saudi Data and Artificial Intelligence Authority 70B parameters May 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
Saudi Data and Artificial Intelligence Authority
Organisation type
Industry,Government
Country
Saudi Arabia
Published
21 May 2024
Authors
Saudi Data and Artificial Intelligence Authority

What it does

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

Domain
Language
Task
Language modeling/generation, Translation, Question answering
Base model
Llama 2-70B
Numerical format
BF16

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
70B
Training data
600,000,000,000 tokens

"For the ALLaM-70B model, we only train up to 600B tokens"

Epochs
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
1.1 × 10²⁴ FLOP

Llama 70B: 8.1e+23 Finetune: 6*70000000000*600000000000=252000000000000000000000 Total: 1062000000000000000000000

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

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

not yet released

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
Why it is tracked
SOTA improvement

SOTA at Arabic MMLU benchmarks, all results in this paper: https://openreview.net/pdf?id=MscdsFVZrN

Record confidence
Confident
Citations
69

Sources

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

Reference
ALLaM: Large Language Models for Arabic and English
Last updated
25 May 2026

What the numbers mean

Where it came from

ALLaM adapted 70B was published by Saudi Data and Artificial Intelligence Authority, in Saudi Arabia, in May 2024. The organisation is categorised as industry,Government.

It works in Language, and is recorded as doing language modeling/generation, Translation, Question answering.

It builds on Llama 2-70B, which is why it shares that model's general shape and size.

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

What went into building it

The training run consumed about 1.1 × 10²⁴ FLOP, on NVIDIA A100. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

The training set ran to roughly 600,000,000,000 tokens.

Its inclusion criterion is sOTA improvement.

Answers

ALLaM adapted 70B — common questions

01

Who created ALLaM adapted 70B?

ALLaM adapted 70B was published by Saudi Data and Artificial Intelligence Authority, based in Saudi Arabia, categorised as industry,Government.

02

When was ALLaM adapted 70B released?

ALLaM adapted 70B was published in May 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.

03

What is ALLaM adapted 70B used for?

ALLaM adapted 70B works in Language, and is recorded as handling language modeling/generation, Translation, Question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

04

How much compute was used to train ALLaM adapted 70B?

Around 1.1 × 10²⁴ FLOP, on NVIDIA A100. 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.

05

What GPU do I need to run ALLaM adapted 70B?

None. ALLaM adapted 70B 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.

06

Is ALLaM adapted 70B open source?

No. ALLaM adapted 70B has not had its weights published, so it exists only as a service controlled by its owner.

07

How many parameters does ALLaM adapted 70B have?

ALLaM adapted 70B has 70B 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.

Source

Original publication

Record last updated 25 May 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.