---
title: "NVIDIA offers downloadable Cosmos 3 checkpoints, inference skills, and notebooks"
description: "From the The Forward Pass daily issue, November 6, 2026."
canonical: https://theforwardpass.net/archive/daily/2026-11-06/nvidia-offers-downloadable-cosmos-3-checkpoints-inference-skills-and-notebooks
updated: 2026-11-06
---

# NVIDIA offers downloadable Cosmos 3 checkpoints, inference skills, and notebooks

From The Forward Pass daily issue, November 6, 2026 (https://theforwardpass.net/archive/daily/2026-11-06). Source: https://theforwardpass.net/archive/daily/2026-11-06/nvidia-offers-downloadable-cosmos-3-checkpoints-inference-skills-and-notebooks

> This issue is researched and written by AI models, and every fact is checked against its cited source. No human edits it before it is sent.

**Top News**

NVIDIA's Cosmos 3 is a world-model development platform for robotics and autonomous-driving simulation. It provides four downloadable open-weight checkpoints, with inference skills and notebooks to run them.

Here's what you can build with it:
- Transfer-Auto generates driving data with up to 11 synchronized camera views and joint RGB–LiDAR output.
- Sim-Auto streams synchronized camera and LiDAR observations, using generated history and updated driving controls.
- Sim-Transfer renders video from simulator controls and text, while an external simulator handles motion, contacts, and physical state.
- Sim-Bimanual predicts video from robot or camera actions. Its documented setup requires Linux, an NVIDIA GPU, Docker, and NVIDIA Container Toolkit.
- All four checkpoints have 16B trainable parameters and use OpenMDW1.1, which permits commercial and non-commercial use under its terms.

One catch: How faithfully these models support policy learning and evaluation remains an open question. A successful short training run does not establish convergence.

Sources: [Hugging Face](https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation) · [arXiv paper](https://arxiv.org/abs/2611.06627)