Mixture-of-Depths
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,McGill University,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms)
- Organisation type
- Industry,Academia,Academia
- Country
- United States of America, Canada
- Published
- 2 April 2024
- Authors
- David Raposo, Sam Ritter, Blake Richards, Timothy Lillicrap, Peter Conway Humphreys, Adam Santoro
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Language modeling/generation
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
- 3B
- Training data
- tokens
Figure 4: "We used the 12.5% capacity MoD variant to perform an isoFLOP analysis for 6e18, 2e19, and 1e20 FLOPs, training models varying in size from 60M to 3B parameters"
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
- 1 × 10²⁰ FLOP
- How it was established
- Reported
Figure 4: "We used the 12.5% capacity MoD variant to perform an isoFLOP analysis for 6e18, 2e19, and 1e20 FLOPs, training models varying in size from 60M to 3B parameters"
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
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
- Citations
- 187
Sources
Where this record came from and when it was last checked.
- Reference
- Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
- Last updated
- 25 May 2026
What the numbers mean
Background
Mixture-of-Depths was published by Google DeepMind,McGill University,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms), in United States of America, in April 2024. It comes out of industry,Academia,Academia.
It works in Language, and is recorded as doing language modeling/generation.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
How it was trained
Training it took roughly 1 × 10²⁰ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.
Answers
Mixture-of-Depths — common questions
Is Mixture-of-Depths open source?
No. Mixture-of-Depths has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Mixture-of-Depths have?
Mixture-of-Depths has 3B parameters. Figure 4: "We used the 12.5% capacity MoD variant to perform an isoFLOP analysis for 6e18, 2e19, and 1e20 FLOPs, training models varying in size from 60M to 3B parameters". 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.
Who created Mixture-of-Depths?
Mixture-of-Depths was published by Google DeepMind,McGill University,Mila - Quebec AI (originally Montreal Institute for Learning Algorithms), based in United States of America, categorised as industry,Academia,Academia.
When was Mixture-of-Depths released?
Mixture-of-Depths was published in April 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.
What is Mixture-of-Depths used for?
Mixture-of-Depths works in Language, and is recorded as handling language modeling/generation. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
How much compute was used to train Mixture-of-Depths?
Around 1 × 10²⁰ FLOP. 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.
What GPU do I need to run Mixture-of-Depths?
None. Mixture-of-Depths 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.
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.