Cosmos 3 Super — 显存、速度与本地部署

作者： Jakub Rusinowski · 最后更新： 2026年7月21日

The largest, highest-fidelity tier — a 64B-parameter two-tower MoT built on a dense 32B transformer backbone. Super is the model you post-train: NVIDIA positions it for building custom robotics and autonomous-vehicle world models, generating high-quality synthetic training video and predicting long-horizon action sequences with strong physics accuracy. NVIDIA reports Cosmos 3 Super takes the highest overall PAI-Bench-G scores on both text-to-video and image-to-video across all models tested, including closed-source. Datacenter-class hardware: ~128 GB VRAM at BF16 (roughly halved at FP8), so a Hopper/Blackwell multi-GPU node (H100/H200/B200 class). Omnimodal I/O (text, image, video, audio, action). OpenMDW-1.1. Specs from launch coverage and the Hugging Face model card — verify before relying on them.

Cosmos 3 Super 在 BF16 下约需 39 GB 显存——量化权重加框架开销，不含 KV 缓存。在 Apple Silicon 上，这部分来自统一内存。