ALLaM adapted 70B
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
- Epochs
- 1
"For the ALLaM-70B model, we only train up to 600B 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
- 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
- Record confidence
- Confident
- Citations
- 69
SOTA at Arabic MMLU benchmarks, all results in this paper: https://openreview.net/pdf?id=MscdsFVZrN
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 the country recorded as Saudi Arabia, during May 2024. The publishing organisation is categorised as industry,Government.
It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Translation, Question answering.
It builds on Llama 2-70B. Most models at this scale are adapted from an existing base rather than built from nothing.
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 hardware recorded as NVIDIA A100. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 600,000,000,000 tokens of text.
Its inclusion criterion: sOTA improvement.
Answers
ALLaM adapted 70B — common questions
ALLaM adapted 70B— who created it?
It was published by Saudi Data and Artificial Intelligence Authority, based in Saudi Arabia, an organisation categorised as industry,Government.
ALLaM adapted 70B— when was it released?
It 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.
ALLaM adapted 70B— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Translation, Question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
ALLaM adapted 70B— how much compute was used to train it?
Training consumed around 1.1 × 10²⁴ FLOP, on hardware recorded as 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.
ALLaM adapted 70B— 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.
ALLaM adapted 70B— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
ALLaM adapted 70B— how many parameters does it have?
It has a parameter count of 70B. 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.
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.