{"slug": "nvidia-releases-cosmos-3-family-four-open-weight-nano-checkpoints-for-world", "title": "Nvidia Releases Cosmos 3 Family, Four Open-Weight Nano Checkpoints for Interactive World Simulation", "summary": "Nvidia released four open-weight checkpoints in its new Cosmos 3 family, all post-trained variants of the 16-billion-parameter Cosmos 3 Nano foundation model, under the Linux Foundation's OpenMDW-1.1 license that permits commercial and non-commercial use. The checkpoints — Cosmos3-Nano-Transfer-Auto, Cosmos3-Nano-Sim-Auto, Cosmos3-Nano-Sim-Transfer and Cosmos3-Nano-Sim-Bimanual — target interactive world simulation for robotics and autonomous driving, generating multi-view camera video (up to 11 views) and LiDAR, streaming closed-loop driving observations, converting simulator spatial controls to photorealistic RGB, and predicting bimanual robot observations. Nvidia calls Cosmos 3 the first fully open omni-model for physical AI, built on a Mixture-of-Transformers architecture that handles language, image, video, audio and action in one model, with Edge (4B total, based on a 2B transformer) among three defined scales.", "body_md": "# Nvidia Releases Cosmos 3 Family, Four Open-Weight Nano Checkpoints for Interactive World Simulation\n\nNvidia has published four open-weight checkpoints under its new Cosmos 3 platform, targeting researchers building interactive world simulators for robotics and autonomous driving. The models—Cosmos3-Nano-Transfer-Auto, Cosmos3-Nano-Sim-Auto, Cosmos3-Nano-Sim-Transfer, and Cosmos3-Nano-Sim-Bimanual—are post-trained variants of the 16-billion-parameter Cosmos 3 Nano foundation model, released under the Linux Foundation's OpenMDW-1.1 license [\\[7\\]](https://research.nvidia.com/labs/cosmos-lab/cosmos3/technical-report.pdf), which permits commercial and non-commercial use [\\[1\\]](https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation). Nvidia describes Cosmos 3 as the first fully open omni-model for physical AI [\\[5\\]](https://huggingface.co/nvidia), a claim that rests on the model's unified handling of language, image, video, audio, and action within a single Mixture-of-Transformers (MoT) architecture [\\[7\\]](https://research.nvidia.com/labs/cosmos-lab/cosmos3/technical-report.pdf).\n\n## Four Checkpoints, Four Simulation Tasks\n\nEach checkpoint addresses a different simulation workflow:\n\n- **Transfer-Auto** generates synchronized multi-view camera video (up to 11 views) and LiDAR from structured driving scenarios and text prompts, intended for offline synthetic data generation[\\[1\\]](https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation) .\n- **Sim-Auto** is a causally distilled, few-step streaming variant of Transfer-Auto that produces successive chunks of camera and LiDAR observations for closed-loop driving simulation[\\[1\\]](https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation) .\n- **Sim-Transfer** converts simulator-produced spatial controls (depth, segmentation, blur) plus a text prompt into photorealistic RGB video, leaving physics and ground-truth state to an external simulator[\\[1\\]](https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation) .\n- **Sim-Bimanual** predicts the next visual observation from a bimanual robot's actions, supporting YAM and AgiBot embodiments controlled by policy or human-operated joysticks[\\[1\\]](https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation) .\n\nAll four share a four-stage post-training recipe: bidirectional adaptation on full clips, teacher-forcing causal training, consistency distillation, and self-forcing distribution-matching distillation on the student's own rollouts [\\[3\\]](https://research.nvidia.com/labs/cosmos-lab/cosmos-simulation/technical-report.pdf). The consistency distillation stage trains a student that generates each chunk in a few denoising steps; the optimized Bimanual setup predicts two latent time steps per chunk [\\[1\\]](https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation). The technical report notes that policy-driven closed-loop validation remains separate from the reported benchmarks [\\[3\\]](https://research.nvidia.com/labs/cosmos-lab/cosmos-simulation/technical-report.pdf).\n\n## Architecture: One Model, Multiple Modes\n\nCosmos 3 uses a MoT backbone with separate reasoner and generator towers that share a unified representation space [\\[7\\]](https://research.nvidia.com/labs/cosmos-lab/cosmos3/technical-report.pdf). Language tokens are processed autoregressively by the reasoner; vision, audio, and action tokens are diffused by the generator, with joint attention allowing the generator to condition on the reasoner's output [\\[7\\]](https://research.nvidia.com/labs/cosmos-lab/cosmos3/technical-report.pdf). The same weights can operate as a vision-language model, text-to-image/video generator, video-transfer model, forward/inverse dynamics model, or joint video-action policy by changing which tokens are clean or noisy at inference [\\[7\\]](https://research.nvidia.com/labs/cosmos-lab/cosmos3/technical-report.pdf).\n\nThree scales are defined: Edge (4B total, based on a 2B transformer), Nano (16B total, based on an 8B transformer), and Super (64B total, based on a 32B transformer) [\\[7\\]](https://research.nvidia.com/labs/cosmos-lab/cosmos3/technical-report.pdf). Only Nano and Super checkpoints are released so far; Edge is slated for a later release [\\[7\\]](https://research.nvidia.com/labs/cosmos-lab/cosmos3/technical-report.pdf). The four new checkpoints are all Nano-scale, 16B-parameter models [\\[1\\]](https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation).\n\n## Licensing and Developer Tooling\n\nCode, model checkpoints, curated synthetic datasets, and evaluation benchmarks are released under OpenMDW-1.1 [\\[7\\]](https://research.nvidia.com/labs/cosmos-lab/cosmos3/technical-report.pdf). Nvidia also provides Cosmos Framework—an open, modular codebase for training, post-training (including LoRA, SFT, GRPO, PPO, OPD, DiffusionNFT), optimization (distillation, quantization), and inference across Hugging Face Diffusers, PyTorch, SGLang, vLLM-Omni, vLLM, TRT-LLM, and TRT-Edge-LLM [\\[2\\]](https://developer.nvidia.com/blog/build-world-models-for-interactive-simulation-with-nvidia-cosmos). For production deployment, Cosmos NIM microservices offer optimized containers with speculative decoding (measured 2–3× speedup on H200), quantization, and KV-cache-aware routing [\\[2\\]](https://developer.nvidia.com/blog/build-world-models-for-interactive-simulation-with-nvidia-cosmos). The NIM path requires an NGC API key and Docker; the open Framework path runs on Linux with an Nvidia GPU, Docker, and the Nvidia Container Toolkit [\\[1\\]](https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation)[\\[2\\]](https://developer.nvidia.com/blog/build-world-models-for-interactive-simulation-with-nvidia-cosmos).\n\n## Benchmark Claims and Independent Verification\n\nThe Cosmos 3 technical report states: \"Our post-trained Cosmos 3 models were ranked as the best open-source Text-to-Image and Image-to-Video models by Artificial Analysis, and the best policy model by RoboArena at the time the technical report was written\" [\\[7\\]](https://research.nvidia.com/labs/cosmos-lab/cosmos3/technical-report.pdf). These rankings reflect the state of those leaderboards at the time of writing. Table 1 in that report shows Cosmos3-Super leads on Text-to-Image (91.36 vs. 90.85 for Gemini 3 Pro Image), while both Super and Nano outperform baselines on Text-to-Video (80.0/79.4 vs. 79.1 for Veo-3.1) and robot forward dynamics (26.0/25.5 vs. 23.0 for Ctrl-World) [\\[7\\]](https://research.nvidia.com/labs/cosmos-lab/cosmos3/technical-report.pdf). These results come from Nvidia's own evaluations in the technical report.\n\n## What Remains Unknown\n\n- The \"200+ releases\" figure cited in Nvidia's broader open-data catalog spans Physical AI, robotics, autonomous vehicles, biology, drug discovery, retrieval and evaluation benchmarks, and sovereign AI—not exclusively Cosmos 3 checkpoints [\\[5\\]](https://huggingface.co/nvidia) .\n- Hardware minimums for the open Framework are not specified; the published vLLM-Omni setup was tested on a single GB200, explicitly noted as \"not a minimum-memory specification\" [\\[1\\]](https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation) .\n- Cosmos3-Edge weights are not yet available, and no timeline is given.\n- Closed-loop policy evaluation results for the four new checkpoints are not included in the technical report [\\[3\\]](https://research.nvidia.com/labs/cosmos-lab/cosmos-simulation/technical-report.pdf) .\n\nNvidia is hosting a livestream on November 5 to demonstrate the Framework [\\[2\\]](https://developer.nvidia.com/blog/build-world-models-for-interactive-simulation-with-nvidia-cosmos). The checkpoints, technical report, and Framework code are accessible via Hugging Face and GitHub [\\[1\\]](https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation)[\\[3\\]](https://research.nvidia.com/labs/cosmos-lab/cosmos-simulation/technical-report.pdf)[\\[6\\]](https://github.com/NVIDIA/cosmos-framework).\n\n## Sources\n\n1. [New NVIDIA Cosmos 3 Open Models for Interactive World ...](https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation) (huggingface.co)\n2. [Build World Models for Interactive Simulation with NVIDIA ...](https://developer.nvidia.com/blog/build-world-models-for-interactive-simulation-with-nvidia-cosmos) (developer.nvidia.com)\n3. [\\[PDF\\] Interactive World Simulation with Cosmos for Physical AI](https://research.nvidia.com/labs/cosmos-lab/cosmos-simulation/technical-report.pdf) (research.nvidia.com)\n4. [NVIDIA Open Models for Physical AI webinar](https://www.nvidia.com/en-us/events/webinars/aps-open-models-for-physical-ai) (nvidia.com)\n5. [nvidia (NVIDIA)](https://huggingface.co/nvidia) (huggingface.co)\n6. [GitHub - NVIDIA/cosmos-framework: Our inference and training framework to run on the Cosmos Models · GitHub](https://github.com/NVIDIA/cosmos-framework) (github.com)\n7. [Cosmos World Foundation Model Platform for Physical AI](https://research.nvidia.com/labs/cosmos-lab/cosmos3/technical-report.pdf) (research.nvidia.com)", "url": "https://wpnews.pro/news/nvidia-releases-cosmos-3-family-four-open-weight-nano-checkpoints-for-world", "canonical_source": "https://epyhia.com/nvidia-releases-cosmos-3-family-four-open-weight-nano-checkpoints-for", "published_at": "2026-11-09 16:44:42+00:00", "updated_at": "2026-11-09 17:21:01.760646+00:00", "lang": "en", "topics": ["artificial-intelligence", "robotics", "autonomous-vehicles", "ai-research", "generative-ai"], "entities": ["Nvidia", "Cosmos 3", "Cosmos 3 Nano", "Cosmos3-Nano-Transfer-Auto", "Cosmos3-Nano-Sim-Auto", "Cosmos3-Nano-Sim-Transfer", "Cosmos3-Nano-Sim-Bimanual", "Linux Foundation"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/nvidia-releases-cosmos-3-family-four-open-weight-nano-checkpoints-for-world", "markdown": "https://wpnews.pro/news/nvidia-releases-cosmos-3-family-four-open-weight-nano-checkpoints-for-world.md", "text": "https://wpnews.pro/news/nvidia-releases-cosmos-3-family-four-open-weight-nano-checkpoints-for-world.txt", "jsonld": "https://wpnews.pro/news/nvidia-releases-cosmos-3-family-four-open-weight-nano-checkpoints-for-world.jsonld"}}