world model
Dreamer 4
First agent to obtain Minecraft diamonds purely from offline data; beats OpenAI VPT offline with 100x less data.
Levelmodel
Classworld model
Parametersnot in the notes
Contextnot in the notes
ReleasedSep 2025
Opennessunknown
Runs onsingle datacentre GPU
Statusactive
Lineage
successor
DreamerV3 is the parent (successor)medium confidencenotesWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.
Identity
- Developer
- Google DeepMind
- Family
- Dreamer
- Released
- Sep 2025 sourcesregistry date
- Weights published
- –
- Record checked
- 10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- other New objective and architecture; real-time interactive inference on a single GPU
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- not in the notes
- Output
- not in the notes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- unknown
- Licence
- not in the notes sources
- Access routes
- research only
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- single datacentre GPU
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Industry Use Cases
No industry use case links this model.
Links
ModelDreamer 4Google DeepMind, world model
Dreamer 4Google DeepMind, world modelUse Casesnone recorded
Who Runs Itnone recorded
Organisations 1
Sources
- Training Agents Inside of Scalable World Models danijar.com https://danijar.com/project/dreamer4/
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Dreamer 4", https://aurion.semai.id/models/google-deepmind-dreamer-4/, records of October 2026.