Embodied Foundation Models
-
NVIDIA Cosmos 3 Edge
Hugging Face: https://huggingface.co/nvidia/Cosmos3-Edge, https://huggingface.co/collections/nvidia/cosmos3
GitHub: https://github.com/nvidia/cosmos
Website: https://research.nvidia.com/labs/cosmos-lab/cosmos3/
White paper: https://research.nvidia.com/labs/cosmos-lab/cosmos3/technical-report.pdfDeveloper: NVIDIA
Released: July 2026
Variants: Cosmos3-Edge, Cosmos3-Edge-Policy-DROID
Parameters: 4B
Context: Reasoner: 256,000 tokens / Generator text input: 4,096 tokens
Architecture: Mixture-of-Transformers, two towers: an autoregressive transformer for text, a diffusion transformer for image/video/action generation
License: OpenMDW 1.1
Modalities: Text + Image + Video + Action trajectory in / Text + Image + Video + Action out
Formats: safetensors via Hugging Face, PyTorch (NVIDIA-proprietary inference only, BF16)
Runs on: NVIDIA consumer GPU (Linux), Jetson (Linux) -
Tencent Hy-Embodied-RxBrain-1.0
Hugging Face: https://huggingface.co/tencent/Hy-Embodied-RxBrain-1.0
GitHub: https://github.com/Tencent-Hunyuan/Hy-Embodied-RxBrain-1.0
Website: https://tairos.tencent.com/openSourceModels/hy-embodied-rxbrain-1.0
Technical report: https://arxiv.org/abs/2607.14187Developer: Tencent Robotics X, Futian Laboratory, Tencent Hy Team
Released: July 2026
Parameters: ~6.2B
Architecture: Unified Mixture-of-Transformers, modality-specific text, vision, and generation pathways
License: Apache 2.0
Modalities: Text + Image + Video
Runs on: NVIDIA GPU, CUDA 12.x, Linux recommended
Formats: safetensors
On disk: 12.42GB safetensors -
NVIDIA Isaac GR00T N1.7
Hugging Face: https://huggingface.co/nvidia/GR00T-N1.7-3B, https://huggingface.co/collections/nvidia/gr00t-n17
GitHub: https://github.com/NVIDIA/Isaac-GR00T
Website: https://developer.nvidia.com/isaac/gr00t
Docs: https://huggingface.co/blog/nvidia/gr00t-n1-7Developer: NVIDIA
Released: April 2026
Variants: N1, N1.5, N1.6, N1.7
Parameters: 3B
Architecture: Dual-system VLA pairing a Cosmos-Reason2-2B vision-language backbone for task/subtask reasoning with a flow-matching diffusion transformer conditioned on the reasoning output
License: NVIDIA Open Model License Agreement
Modalities: RGB camera frames + language instruction + robot proprioception in / continuous robot action vectors out
Runs on: Desktop GPU, Datacenter GPU, or NVIDIA Jetson edge modules; NVIDIA only
Formats: safetensors, 2 shards
On disk: 6.91GB -
NVIDIA Cosmos Reason 2
Hugging Face: https://huggingface.co/nvidia/Cosmos-Reason2-8B, https://huggingface.co/nvidia/Cosmos-Reason2-2B, https://huggingface.co/nvidia/Cosmos-Reason2-32B
Website: https://build.nvidia.com/nvidia/cosmos-reason2-8b
Docs: https://huggingface.co/blog/nvidia/nvidia-cosmos-reason-2-brings-advanced-reasoningDeveloper: NVIDIA
Released: January 2026
Variants: 2B, 8B, 32B
Parameters: 8.77B (8B tier)
Architecture: Qwen3-VL fine-tune post-trained for physical-AI reasoning
License: NVIDIA Open Model License Agreement
Modalities: Image/video + text in / spatio-temporal reasoning, trajectory, point, and bounding-box predictions out
Runs on: NVIDIA GPU
Formats: safetensors, 4 shards (8B tier)
On disk: 17.53GB (8B tier) -
Unitree UnifoLM-VLA-0
Hugging Face: https://huggingface.co/unitreerobotics/Unifolm-VLM-Base, https://huggingface.co/unitreerobotics/Unifolm-VLA-Base, https://huggingface.co/unitreerobotics/Unifolm-VLA-Libero
GitHub: https://github.com/unitreerobotics/unifolm-vla
Website: https://unigen-x.github.io/unifolm-vla.github.ioDeveloper: Unitree Robotics
Released: January 2026
Variants: VLM-Base, VLA-Base, VLA-LIBERO
Architecture: Qwen2.5-VL-7B backbone with a diffusion-transformer flow-matching action head; continued pretraining fuses 2D/3D spatial understanding with action-chunking prediction and forward/inverse dynamics constraints
Modalities: Multi-view RGB + robot state + language instruction in / continuous manipulation actions out
Formats: PyTorch checkpoint
On disk: VLA-Base 18.98GB -
Alibaba DAMO RynnBrain 1.1
Hugging Face: https://huggingface.co/Alibaba-DAMO-Academy/RynnBrain1.1-2B, https://huggingface.co/Alibaba-DAMO-Academy/RynnBrain1.1-9B, https://huggingface.co/Alibaba-DAMO-Academy/RynnBrain1.1-122B-A10B
GitHub: https://github.com/alibaba-damo-academy/RynnBrain
Technical report: https://arxiv.org/abs/2602.14979Developer: Alibaba DAMO Academy
Released: July 2026
Variants: 2B, 9B, 122B-A10B
Parameters: 9.41B (9B checkpoint)
Architecture: Decoder-only vision-language transformer (dense 2B/9B, sparse-MoE 122B-A10B) on a Qwen3.5 base
License: Apache License 2.0
Modalities: Image/video + language in / spatial/3D grounding, contact-point and affordance predictions, task planning out
Formats: safetensors
On disk: 18.82GB (9B checkpoint)
