GenCast
No estimate
No hardware requirements for this model
This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.
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
- Google DeepMind
- Organisation type
- Industry
- Country
- United States of America
- Published
- 1 May 2024
- Authors
- Ilan Price, Alvaro Sanchez-Gonzalez, Ferran Alet, Tom R. Andersson, Andrew El-Kadi, Dominic Masters, Timo Ewalds, Jacklynn Stott, Shakir Mohamed, Peter Battaglia, Remi Lam, Matthew Willson
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Earth science
- Task
- Weather forecasting
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.
- Training data
- tokens
Stage 1: 2 million training steps. batch size 32 Stage 2: 64 000 further training steps. batch size 32
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
- 8.2 × 10²⁰ FLOP
- How it was established
- Hardware
The model was trained for 120 hours on 32 TPUv5. Assuming it was TPUv5e, bf16 precision: 197000000000000 FLOP/s * 120 hours * 3600 s/hour * 32 instances * 0.3 [assumed utilization] = 8.169984e+20 FLOP
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
- Google TPU v5e
- Chips used
- 32
- Chip-hours
- 120
- Power draw
- 14.2 kW
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
- Open — downloadable
- Model access
- Open weights (non-commercial)
- Training code
- Open source
Apache 2.0 for training and inference code https://github.com/google-deepmind/graphcast CC BY-NC-SA 4.0 for weights
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- SOTA improvement
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- GenCast: Diffusion-based ensemble forecasting for medium-range weather
- Last updated
- 28 November 2025
What the numbers mean
What this model is
GenCast was published by Google DeepMind, in the country recorded as United States of America, during May 2024. The publishing organisation is categorised as industry.
It works in the domain of Earth science, and is recorded as performing the task of weather forecasting.
The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.
What went into building it
The training run consumed about 8.2 × 10²⁰ FLOP, on hardware recorded as Google TPU v5e. That figure measures what producing the model cost, and has no bearing on how fast it answers.
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Answers
GenCast — common questions
GenCast— how much compute was used to train it?
Training consumed around 8.2 × 10²⁰ FLOP, on hardware recorded as Google TPU v5e. 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.
GenCast— what GPU do I need to run it?
We cannot say. It has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.
GenCast— is it open source?
Its weights are published, so it can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
GenCast— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
GenCast— who created it?
It was published by Google DeepMind, based in United States of America, an organisation categorised as industry.
GenCast— 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.
GenCast— what is it used for?
It works in the domain of Earth science, and is recorded as handling the task of weather forecasting. These are the areas it was designed around; they describe intent rather than a hard boundary.
GenCast— where can I download it?
The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
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.