RFM-1
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
- Covariant
- Organisation type
- Industry
- Country
- United States of America
- Published
- 11 March 2024
- Authors
- Andrew Sohn, Anusha Nagabandi, Carlos Florensa, Daniel Adelberg, Di Wu, Hassan Farooq, Ignasi Clavera, Jeremy Welborn, Juyue Chen, Nikhil Mishra, Peter Chen, Peter Qian, Pieter Abbeel, Rocky Duan, Varun Vijay, Yang Liu
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Robotics, Vision, Video
- Task
- Robotic manipulation, Image captioning, Video description
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
- 8B
- Training data
- tokens
8b
from here https://covariant.ai/insights/rfm-1-update-higher-quality-grasp-accuracy/ 5*10^9 tokens
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
- 2.4 × 10²⁰ FLOP
- How it was established
- Operation counting
6 FLOP / token / parameter * 5000000000 tokens * 8*10^9 parameters = 2.4e+20 FLOP I am not confident about amount of epochs and whether the model is dense
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
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- Introducing RFM-1: Giving robots human-like reasoning capabilities
- Last updated
- 28 November 2025
What the numbers mean
What this model is
RFM-1 was published by Covariant, in United States of America, in March 2024. It comes out of industry.
It works in Robotics, Vision, Video, and is recorded as doing robotic manipulation, Image captioning, Video description.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
Producing it required around 2.4 × 10²⁰ FLOP of arithmetic, which is a statement about the training budget rather than about inference.
Answers
RFM-1 — common questions
How many parameters does RFM-1 have?
RFM-1 has 8B parameters. 8b. 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 RFM-1?
RFM-1 was published by Covariant, based in United States of America, categorised as industry.
When was RFM-1 released?
RFM-1 was published in March 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 RFM-1 used for?
RFM-1 works in Robotics, Vision, Video, and is recorded as handling robotic manipulation, Image captioning, Video description. These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train RFM-1?
Around 2.4 × 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 RFM-1?
None. RFM-1 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 RFM-1 open source?
No. RFM-1 has not had its weights published, so it exists only as a service controlled by its owner.
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.