MODEL REFERENCE / nvidia

nvidia/Cosmos3-Super

Frontier-scale 64B omnimodal world model (Mixture-of-Transformers) for advanced multimodal understanding, world simulation, future prediction, action reasoning, and Physical AI

64B omnimodal world model — ~55s/video on 8×H200 with HSDP + ulysses

View on HuggingFace View on ModelScope

vLLMdense64B262,144 ctxvLLM 0.21.0+vLLM-Omninightlyomni

02 / Configure

Configure serving

Choose engine, hardware and deployment options. The command updates as you go.

03 / Understand

Technical notes

Model notes and examples