Granite 13B
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
- IBM
- Organisation type
- Industry
- Country
- United States of America
- Published
- 30 November 2023
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Chat, Language modeling/generation, Question answering, Text summarization
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
- 2,500,000,000,000 tokens
- Epochs
- 1
13 billion
2.5T tokens, 1.875T words at 0.75 words/token https://www.ibm.com/docs/en/cloud-paks/cp-data/5.0.x?topic=models-granite-13b-chat-v2-model-card
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
- 2.4 × 10²³ FLOP
- How it was established
- Hardware,Operation counting
Estimate using hardware: "Granite.13b.v1 used 256 A100 GPUs for 1056 hours and 120 TFLOPs. Granite.13b.v2 was trained on the same infrastructure for an additional 1152 hours with 120 TFLOPS, bringing the total to 2208 hours" Seems like 120 TFLOPS is the output per GPU after utilization, though they don't explicitly explain that part. That's 38% utilization. 256 * 2208 * 3600 * 120 TFLOPS = 2.44e23 Using 6ND: "The second version of the granite.13b models leverages an updated base model train…
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
- Wall-clock time
- 2,208 hours (92 days)
"Granite.13b.v1 used 256 A100 GPUs for 1056 hours and 120 TFLOPs. Granite.13b.v2 was trained on the same infrastructure for an additional 1152 hours with 120 TFLOPS, bringing the total to 2208 hours"
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
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
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- Granite Foundation Models
- Last updated
- 28 November 2025
What the numbers mean
Background
Granite 13B was published by IBM, in the country recorded as United States of America, during November 2023. The publishing organisation is categorised as industry.
It works in the domain of Language, and is recorded as performing the task of chat, Language modeling/generation, Question answering, Text summarization.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
Training it took a computation budget of roughly 2.4 × 10²³ 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 2,500,000,000,000 tokens of text.
Answers
Granite 13B — common questions
Granite 13B— how much compute was used to train it?
Training consumed around 2.4 × 10²³ 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.
Granite 13B— 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.
Granite 13B— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
Granite 13B— how many parameters does it have?
It has a parameter count of 13B. 13 billion. 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.
Granite 13B— who created it?
It was published by IBM, based in United States of America, an organisation categorised as industry.
Granite 13B— when was it released?
It was published in November 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
Granite 13B— what is it used for?
It works in the domain of Language, and is recorded as handling the task of chat, Language modeling/generation, Question answering, Text summarization. These are the areas it was designed around; they describe intent rather than a hard boundary.
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.