AI Agent StoreAlibaba DAMO Academy · Download documented
RynnUnify Base · visual planning research
Explore plans for a changing physical scene by combining written reasoning with generated video predictions. This is a research setup for scene understanding and visual planning.
First reviewed 2026-10-27 · Checked 2026-11-03. The launch date has not been confirmed.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Try it on your hardware and tasks before relying on it.
What you can use today
You download the model files and supply the hardware and software to run them. Capacity is the amount of information a request can contain; settings and available memory can limit what fits.
Exact download ID: Alibaba-DAMO-Academy/RynnUnify-Base. The 16B architecture pairs an 8B reasoner with an 8B video generator. The project includes training and evaluation paths that choose whether to answer directly or generate visual evidence. Its separate world-action extension is not proof that this base download can directly control a robot.
Requires the compatible Cosmos framework and project-specific setup. The card labels the checkpoint Apache 2.0; check the base-model and component terms. No ready-to-use hosted API is established.
Context and maximum output limits are not verified. Video duration and research rollout examples are not general token limits.
No hosted token price or measured local cost is established. Project benchmark and robot demonstrations remain publisher evidence, not independent results here.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Include the time and hardware needed to run it.
Compare caching and long-context costs ↗