DolphinGemma
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
- Google DeepMind,Georgia Institute of Technology,Wild Dolphin Project
- Organisation type
- Industry,Academia,Research collective
- Country
- United States of America
- Published
- 14 April 2025
- Authors
- Denise Herzing, Thad Starner
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Audio
- Task
- Audio generation, Speech recognition (ASR), Audio classification
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
- 400M
- Training data
- tokens
400M
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
"Recognizing the value of collaboration in scientific discovery, we’re planning to share DolphinGemma as an open model this summer. " [2025]
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
- DolphinGemma: How Google AI is helping decode dolphin communication
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
DolphinGemma was published by Google DeepMind,Georgia Institute of Technology,Wild Dolphin Project, in United States of America, in April 2025. industry,Academia,Research collective is the category the publisher falls under.
It works in Audio, and is recorded as doing audio generation, Speech recognition (ASR), Audio classification.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Answers
DolphinGemma — common questions
Who created DolphinGemma?
DolphinGemma was published by Google DeepMind,Georgia Institute of Technology,Wild Dolphin Project, based in United States of America, categorised as industry,Academia,Research collective.
When was DolphinGemma released?
DolphinGemma was published in April 2025.
What is DolphinGemma used for?
DolphinGemma works in Audio, and is recorded as handling audio generation, Speech recognition (ASR), Audio classification. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run DolphinGemma?
None. DolphinGemma 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 DolphinGemma open source?
No. DolphinGemma has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does DolphinGemma have?
DolphinGemma has 400M parameters. 400M. 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.