Relational Memory Core
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
- DeepMind,University College London (UCL)
- Organisation type
- Industry,Academia
- Country
- United Kingdom of Great Britain and Northern Ireland
- Published
- 5 June 2018
- Authors
- Adam Santoro, Ryan Faulkner, David Raposo, Jack Rae, Mike Chrzanowski, Theophane Weber, Daan Wierstra, Oriol Vinyals, Razvan Pascanu, Timothy Lillicrap
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling
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
- 4,000,000,000 tokens
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
looks like code for the architecture, but not experiment code: https://github.com/google-deepmind/sonnet/blob/v1/sonnet/python/modules/relational_memory.py
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
- Citations
- 235
- Benchmark data
- Relational Memory Core
"Finally, we test the RMC on a suite of tasks that may profit from more capable relational reasoning across sequential information, and show large gains in RL domains (e.g. Mini PacMan), program evaluation, and language modeling, achieving state-of-the-art results on the WikiText-103, Project Gutenberg, and GigaWord datasets."
Sources
Where this record came from and when it was last checked.
- Reference
- Relational recurrent neural networks
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Relational Memory Core was published by DeepMind,University College London (UCL), in United Kingdom of Great Britain and Northern Ireland, in June 2018. industry,Academia is the category the publisher falls under.
It works in Language, and is recorded as doing language modeling.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
The training set ran to roughly 4,000,000,000 tokens.
Its inclusion criterion is sOTA improvement.
Answers
Relational Memory Core — common questions
What GPU do I need to run Relational Memory Core?
None. Relational Memory Core 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 Relational Memory Core open source?
No. Relational Memory Core has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Relational Memory Core have?
No parameter count has been published for Relational Memory Core, which is why no memory or speed figure appears on this page.
Who created Relational Memory Core?
Relational Memory Core was published by DeepMind,University College London (UCL), based in United Kingdom of Great Britain and Northern Ireland, categorised as industry,Academia.
When was Relational Memory Core released?
Relational Memory Core was published in June 2018. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is Relational Memory Core used for?
Relational Memory Core works in Language, and is recorded as handling language modeling. 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.