Cosmos-Reason1 56B
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
- NVIDIA
- Organisation type
- Industry
- Country
- United States of America
- Published
- 19 May 2025
- Authors
- NVIDIA: Alisson Azzolini, Junjie Bai, Hannah Brandon, Jiaxin Cao, Prithvijit Chattopadhyay, Huayu Chen, Jinju Chu, Yin Cui, Jenna Diamond, Yifan Ding, Liang Feng, Francesco Ferroni, Rama Govindaraju, Jinwei Gu, Siddharth Gururani, Imad El Hanafi, Zekun Hao, Jacob Huffman, Jingyi Jin, Brendan Johnson, Rizwan Khan, George Kurian, Elena Lantz, Nayeon Lee, Zhaoshuo Li, Xuan Li, Maosheng Liao, Tsung-Yi…
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Multimodal, Language, Vision, Robotics, Video
- Task
- Language modeling/generation, Visual question answering, Video description, Question answering, Instruction interpretation, Robotic manipulation
- Base model
- Nemotron-H 56B
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
- 56B
- Training data
- tokens
56B
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
Apache 2.0 https://github.com/nvidia-cosmos/cosmos-reason1
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
- From Physical Common Sense To Embodied Reasoning
- Last updated
- 28 November 2025
What the numbers mean
Background
Cosmos-Reason1 56B was published by NVIDIA, in the country recorded as United States of America, during May 2025. It comes out of an organisation categorised as industry.
It works in the domain of Multimodal, Language, Vision, Robotics, Video, and is recorded as performing the task of language modeling/generation, Visual question answering, Video description, Question answering, Instruction interpretation, Robotic manipulation.
It builds on Nemotron-H 56B. That is why it shares the base model's general shape and size.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Answers
Cosmos-Reason1 56B — common questions
Cosmos-Reason1 56B— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
Cosmos-Reason1 56B— how many parameters does it have?
It has a parameter count of 56B. 56B. 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.
Cosmos-Reason1 56B— who created it?
It was published by NVIDIA, based in United States of America, an organisation categorised as industry.
Cosmos-Reason1 56B— when was it released?
It was published in May 2025.
Cosmos-Reason1 56B— what is it used for?
It works in the domain of Multimodal, Language, Vision, Robotics, Video, and is recorded as handling the task of language modeling/generation, Visual question answering, Video description, Question answering, Instruction interpretation, Robotic manipulation. 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.
Cosmos-Reason1 56B— what GPU do I need to run it?
None. This 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.