NVIDIA extends the open Cosmos Framework to GR00T, Qwen and pi0.5 models and publishes Cosmos 3 Nano simulation checkpoints
One toolkit for training, RL and inference across world and robot models, plus checkpoints and memory figures for teams building simulation.
// Key points
- The Cosmos Framework, an open modular toolkit for training, reinforcement learning, optimization and inference, now covers NVIDIA Alpamayo, GR00T, Qwen, pi0.5 and other compatible Hugging Face models, with new DPO, GRPO, PPO, OPD and DiffusionNFT pipelines
- Released checkpoints on Hugging Face include Cosmos3-Nano-Transfer-Auto, Cosmos3-Nano-Sim-Auto, Cosmos3-Nano-Sim-Transfer and Cosmos3-Nano-Sim-Bimanual; Transfer-Auto generates up to 400 frames at 480p or 720p
- Cosmos3-Nano needs 58 GiB of GPU memory for generation in BF16, 44 GiB in FP8 and 31 GiB with FP8 plus offloading; speculative decoding gives roughly 2–3x mean speedups on H200
Builder's takeIf you don't build robots or driving systems, this one can wait. If you do, start with the Nano checkpoints in FP8 and read each model card first: the post itself states no license for the weights, the framework or the NIM containers.
// Background · from #Open models
Full timeline →- Nov 3 AWS distills a GLM-5.3 shopping agent into Qwen3.5-4B: held-out success rises from 0.297 to 0.541, level with the teacher
- Nov 2 NVIDIA introduces NemoClaw open blueprints: OpenClaw, Hermes Agent or LangChain Deep Agents paired with Nemotron models and the OpenShell runtime
- Nov 2 NVIDIA runs Dynamo 1.4.2 on the open-source AI Cluster Runtime: validated recipes pin about 18 Helm charts for GB200 and GB300 NVL72 on EKS