NVIDIA Releases Alpamayo 2 Super: A 34B Parameter VLA Model for Autonomous Driving

drmapavone · x · 2026-08-05

NVIDIA has released Alpamayo 2 Super, an open 34-billion-parameter Vision-Language-Action (VLA) reasoning model designed to accelerate autonomous vehicle (AV) development.

The model combines the 32-billion-parameter NVIDIA Cosmos 3 Super Reasoner with a 2-billion-parameter diffusion-based Action Expert, and is post-trained with reinforcement learning. It is available on Hugging Face under the OpenMDW-1.1 license, allowing commercial deployment without requiring additional permissions.

Related event: NVIDIA Releases Open-Source Autonomous Driving VLA Model Alpamayo 2 Super(12 posts)→

Original post →

More from Embodied

Embodied channel →