NVIDIA / RESEARCH PROFILE
Cosmos3-H-Dreams
An action-conditioned surgical world model that generates video from robot state and action inputs, rather than serving as a general chat assistant.
Source reviewed 2026-10-24 · AiBrainWorX editorial summary
- Creator
- NVIDIA
- Parameters
- 15.17B (publisher)
- Context
- Video/action sequence; not a chat-token specification
- License
- NVIDIA Open Model License
01 / CAPABILITIES
What it is built for
- Mixture-of-Transformers architecture
- Kinematic action conditioning
- Distilled autoregressive video generation
Inputs: Video + robot actions
Publisher/model configuration specification. Usable context depends on deployment resources.
02 / ON YOUR MACHINE
Specialized research deployment
Requires its dedicated research pipeline. It is not compatible with the launcher’s ordinary text-chat workflow and has not been tested locally by us.
Research profile only
Runtime and training workflow
Dedicated research runtime
Separate model-specific training workflow. Training suitability requires exact checkpoint format and prepared data; a catalog entry is not a completed training test.
03 / WHAT IS VERIFIED
Evidence, with context
Source-reviewed research profile; this exact checkpoint has not been benchmarked locally.
We have not added a benchmark number without documenting its test conditions. A model-card capability is not a measured speed or quality guarantee on your hardware.
04 / OWNERSHIP & USE
NVIDIA Open Model License
Custom NVIDIA license, including base-model conditions. Research coverage, not a bundled launcher model.
AiBrainWorX authors this profile and the launcher. NVIDIA remains the model’s creator. Models are not rebranded as our own weights.
05 / GO DEEPER
Original sources & model files
This page is our concise summary, not a mirror of the full upstream card. Review the original documentation and exact artifact before downloading.
Reviewed revision: fd87afe3fd97 · Specifications may change after the review date.
THE CURIOUS SIDE OF AI