Skip to main content
← All open-weight guides

NVIDIA · open weights

Alpamayo 2 Super

An open vision-language-action model aimed at embodied and autonomous systems rather than general chat.

·OpenMDW-1.1·34B total / 32B VLM backbone + action expert
visionlanguageaction
Practical fit
Relevant to robotics and physical-world evaluation, not a drop-in chatbot replacement.
Deployment note
Hardware, simulator, sensor, and safety validation are part of the product decision.