ALLaM adapted13B
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-13B
- 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
- 13B
- Training data
- 5,200,000,000,000 tokens
- Epochs
- 1
3,431,217,579(4.3B) total documents, with a total of 4,587,781,981,546(4.5T) words, and 5.2T 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
- 1.7 × 10²³ FLOP
Finetuning compute: 6*13000000000*1200000000000=9.36e+22 Llama 13B training FLOP: 7.8e+22 Total: 1.716e+23
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
- API access
- Training code
- Unreleased
on IBM watsonx platform https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx
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
- 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
About this model
ALLaM adapted13B was published by Saudi Data and Artificial Intelligence Authority, in Saudi Arabia, in May 2024. It comes out of industry,Government.
It works in Language, and is recorded as doing language modeling/generation, Translation, Question answering.
Its starting point was LLaMA-13B — most models at this scale are adapted from an existing base rather than built from nothing.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
Producing it required around 1.7 × 10²³ FLOP of arithmetic, on NVIDIA A100, which is a statement about the training budget rather than about inference.
It was trained on about 5,200,000,000,000 tokens of text.
Answers
ALLaM adapted13B — common questions
How many parameters does ALLaM adapted13B have?
ALLaM adapted13B has 13B 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.
Who created ALLaM adapted13B?
ALLaM adapted13B was published by Saudi Data and Artificial Intelligence Authority, based in Saudi Arabia, categorised as industry,Government.
When was ALLaM adapted13B released?
ALLaM adapted13B 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.
What is ALLaM adapted13B used for?
ALLaM adapted13B works in Language, and is recorded as handling language modeling/generation, Translation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train ALLaM adapted13B?
Around 1.7 × 10²³ 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.
What GPU do I need to run ALLaM adapted13B?
None. ALLaM adapted13B 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.
Is ALLaM adapted13B open source?
No. ALLaM adapted13B has not had its weights published, so it exists only as a service controlled by its owner.
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.