{"schema":"postcutoff/event@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/e/2026-06-01-nvidia-cosmos-3-open-release/","md":"https://postcutoff.com/e/2026-06-01-nvidia-cosmos-3-open-release/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-06-01-nvidia-cosmos-3-open-release","date":"2026-06-01","date_precision":"day","short_title":"NVIDIA releases Cosmos 3, an open omni-model for physical AI","deck":null,"takeaway":null,"category":"open-source","category_label":"Open source","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Hugging Face blog: Welcome NVIDIA Cosmos 3","url":"https://huggingface.co/blog/nvidia/cosmos-3-for-physical-ai","type":"official","group":"primary","domain":"huggingface.co"},{"n":2,"title":"Cosmos 3 technical report","url":"https://research.nvidia.com/labs/cosmos-lab/cosmos3/technical-report.pdf","type":"paper","group":"primary","domain":"research.nvidia.com"},{"n":3,"title":"nvidia/Cosmos3-Super","url":"https://huggingface.co/nvidia/Cosmos3-Super","type":"code","group":"primary","domain":"huggingface.co"},{"n":4,"title":"NVIDIA Cosmos page","url":"https://www.nvidia.com/en-us/ai/cosmos/","type":"official","group":"primary","domain":"nvidia.com"},{"n":5,"title":"YouTube (NVIDIA): Introducing NVIDIA Cosmos 3","url":"https://www.youtube.com/watch?v=q7Hj3J9SOXw","type":"video","group":"reactions","domain":"youtube.com"}],"official":4,"filed":"2026-09-29","updated":"2026-09-29","orgs":["NVIDIA"],"title":"NVIDIA releases Cosmos 3, an open omni-model for physical AI (world generation, reasoning and actions)","summary":"NVIDIA published open weights for Cosmos 3 (Nano 16B, Super 64B) around 2026-06-01: one Mixture-of-Transformers model that takes text, images, video, audio and robot actions and generates video, images, audio, text or actions, replacing the separate Cosmos Predict, Transfer, Reason and Policy models.","key_facts":["Sizes: Cosmos3-Nano 16B, Cosmos3-Super 64B; Hugging Face, license OpenMDW-1.1 (commercial use allowed), no gating","Inputs: text, images, video, audio, action trajectories; outputs: text, images, video (5-400 frames), 48 kHz audio, actions","Architecture: Mixture-of-Transformers combining autoregressive and diffusion transformers","NVIDIA: best open text-to-image and image-to-video model on Artificial Analysis and best policy model on RoboArena","Announced at GTC 2026-03-16; HF repos went public 2026-05-31; technical report dated 2026-06-22"],"key_numbers":[],"tags":["nvidia","cosmos","world-model","open-weights","robotics","physical-ai"],"science":null,"body_md":"## What happened\n\nCosmos 3 is NVIDIA's first single world foundation model that can generate worlds, reason about physics and output actions. Before it, developers had to chain separate models: Predict 2.5, Transfer 2.5, Reason 2 and Policy.\n\n## Why it matters\n\nIt is the largest open world model aimed at robotics and autonomous vehicles. It also shows the field moving toward models that do both \"world simulation\" and \"policy\" in one, a direction GR00T N2 is also expected to follow.","disputed":[],"related":[{"id":"2026-08-26-nvidia-q2-fy2027-vera-rubin-production","url":"https://postcutoff.com/e/2026-08-26-nvidia-q2-fy2027-vera-rubin-production/","date":"2026-08-26","date_precision":"day","short_title":"NVIDIA posts $96.2B quarter","deck":"Vera Rubin in full production and deploying at major clouds","takeaway":"Vera Rubin shipping in volume in H2 2026 is the compute step-change that 2027 frontier models will be trained and served on; NVIDIA's near-$100B quarter is the clearest financial measure of the AI buildout's scale.","category":"hardware-compute","category_label":"Chips & compute","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":2,"official":1,"filed":"2026-09-29","updated":"2026-09-29","orgs":["NVIDIA"]},{"id":"2026-03-16-nvidia-gtc-2026-robotics-groot-n2-cosmos-3","url":"https://postcutoff.com/e/2026-03-16-nvidia-gtc-2026-robotics-groot-n2-cosmos-3/","date":"2026-03-16","date_precision":"day","short_title":"NVIDIA previews the GR00T N2 world action model and announces Cosmos 3 at GTC 2026","deck":null,"takeaway":"NVIDIA is pitching world-model-based policies and human video as a way to trade scarce robot teleoperation data for compute.","category":"robotics","category_label":"Robotics","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":10,"official":8,"filed":"2026-09-29","updated":"2026-09-29","orgs":["NVIDIA"]}],"people":[],"posts":[],"videos":[{"id":"nvidia-meet-cosmos-3","title":"Meet Cosmos 3: Our Latest Frontier Model for Physical AI","url":"https://postcutoff.com/v/nvidia-meet-cosmos-3/"},{"id":"nvidia-introducing-cosmos-3","title":"Introducing NVIDIA Cosmos 3: The Open Model That Thinks, Generates, and Acts","url":"https://postcutoff.com/v/nvidia-introducing-cosmos-3/"}],"models":[{"id":"cosmos-3","name":"Cosmos 3 (Nano / Super)","url":"https://postcutoff.com/m/cosmos-3/"}],"changes":[{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":32,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":null,"in_training_data":true},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":62,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":1,"in_training_data":false}],"short_url":null}