INTELLECT-1
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
- Prime Intellect,Hugging Face,Arcee AI
- Organisation type
- Industry,Industry,Industry
- Country
- United States of America
- Published
- 29 November 2024
- Authors
- Sami Jaghouar, Jack Min Ong, Manveer Basra, Fares Obeid, Jannik Straube, Michael Keiblinger, Elie Bakouch, Lucas Atkins, Maziyar Panahi, Charles Goddard, Max Ryabinin, Johannes Hagemann
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Approach
- Self-supervised learning
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
- 10B
- Training data
- 1,000,000,000,000 tokens
Table 1. "The total number of tokens in our data mix, processed with the Llama-3 tokenizer, consists of over 6 trillion tokens" however they only train the model with 1T.
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
- 6 × 10²² FLOP
- How it was established
- Operation counting
10B parameters trained on 1T tokens: 6 * 10B * 1T = 6e22
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Wall-clock time
- 1,008 hours (42 days)
"The pre-training of INTELLECT-1 for 1 trillion tokens took place over 42 days, from October 10, 2024, to November 22, 2024"
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
- INTELLECT-1 Technical Report
- Last updated
- 22 December 2025
What the numbers mean
Background
INTELLECT-1 was published by Prime Intellect,Hugging Face,Arcee AI, in the country recorded as United States of America, during November 2024. The publishing organisation is categorised as industry,Industry,Industry.
It works in the domain of Language.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
Producing it required arithmetic totalling around 6 × 10²² FLOP. 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 1,000,000,000,000 tokens of text.
Answers
INTELLECT-1 — common questions
INTELLECT-1— when was it released?
It was published in November 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.
INTELLECT-1— what is it used for?
It works in the domain of Language. These are the areas it was designed around; they describe intent rather than a hard boundary.
INTELLECT-1— how much compute was used to train it?
Training consumed around 6 × 10²² 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.
INTELLECT-1— 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.
INTELLECT-1— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
INTELLECT-1— how many parameters does it have?
It has a parameter count of 10B. 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.
INTELLECT-1— who created it?
It was published by Prime Intellect,Hugging Face,Arcee AI, based in United States of America, an organisation categorised as industry,Industry,Industry.
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.