Skip to content
Friday, 23 October 2026
Tenesys AI News
Subscribe

Cosmos 3

Change history

  1. 22 Oct 2026
    NVIDIA Adds Data, Training and Deployment Tools to Its Cosmos World-Model Platform
    ParameterBeforeNow
    Inference speedBaseline Cosmos 3 NIM microservicesUp to 2x faster in validated configurations, no quality loss
    Model size (MicroAGI case)32B-parameter reasonerDistilled to 8B-parameter Nano model, no accuracy loss
    Video stream monitoring (Metropolis VSS 3.3)Baseline GPU throughput40% more streams monitored on same GPU

News

NVIDIA Adds Data, Training and Deployment Tools to Its Cosmos World-Model Platform

NVIDIA has broadened its Cosmos platform, aimed at building 'world models' for physical AI and robotics, with new data curation blueprints, model fine-tuning support and faster deployment pipelines. The update includes five Cosmos Data Factory blueprints for synthetic and augmented training data, expanded Cosmos Framework support for adapting open models such as GR00T, Alpamayo, QWEN and Pi0.5, and upgraded Cosmos 3 NIM microservices for inference. Companies including Porsche, ANYbotics, Ultralytics and ADNOC are already applying these tools to autonomous vehicle data generation, robot anomaly detection, defect inspection and safety monitoring.

NVIDIA