Cosmos-Reason1-7B is an open-weight multimodal reasoning model from NVIDIA for understanding images and videos alongside text. Developers can download and run the model locally using Python or containerized tooling.
In the Multimodal & vision space, Cosmos Reason1 7B takes a focused approach. It focuses on running an open-weight model for reasoning over text, images, and video. It is built as an open-source project for AI developers and researchers. Cosmos Reason1 7B is open source under the Apache-2.0 license. Cosmos Reason1 7B is available on the command line, and it can be self-hosted.
It is developed by NVIDIA, and it first shipped in 2025. The project is developed in the open on GitHub with 952 stars and 2 commits in the last 90 days. Among its 5 catalogued features are vision-language reasoning, image understanding, and video understanding.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do