OFICIAL NVIDIA Newsroom

NVIDIA Alpamayo 2 Super, the Frontier Open Model for Robotaxis and Autonomous Vehicles, Now Available for Commercial Use

What happened
Based on NVIDIA Newsroom · Aug 04, 2026

NVIDIA released Alpamayo 2 Super, an open reasoning model for autonomous vehicles, now available under the OpenMDW-1.1 license for commercial use on Hugging Face.

Video

Video available

Key points
·
For robotaxis and other autonomous vehicles (AVs), the hardest problems aren’t the everyday scenarios.
·
They’re the rare, complex situations that are difficult to anticipate and train for.
·
Handling these long‑tail events takes more than just object detection and motion prediction.
·
AVs must understand the situation, reason about cause and effect, choose the right action and turn that decision into a safe, comfortable path — all in real time and in a way developers can inspect, validate and trust.
Key numbers
·
NVIDIA Alpamayo 2 Super is now commercially available under the OpenMDW-1.
·
Its 30-billion-parameter scale improves generalization from sparse examples, particularly for multi-agent interactions and complex intersections.
·
NVIDIA released Alpamayo 2 Super, an open reasoning model for autonomous vehicles, now available under the OpenMDW-1.

NVIDIA Alpamayo 2 Super is now commercially available under the OpenMDW-1.1 license, part of the Linux Foundation’s open AI model distribution framework. The model targets rare, complex driving scenarios that conventional systems struggle to handle, offering developers a foundation for reasoning, validation, and deployment. It supports multimodal autonomous driving capabilities within a single model, enabling real-time decision-making for robotaxis and other AV fleets.

The model is built on NVIDIA Cosmos 3 Super Reasoner and enhanced with reinforcement learning, delivering frontier-scale reasoning for cloud-based development. Alpamayo 2 Super ranks first on the LingoQA autonomous driving reasoning benchmark, outperforming several leading models in NVIDIA’s internal testing. Its 30-billion-parameter scale improves generalization from sparse examples, particularly for multi-agent interactions and complex intersections.

Alpamayo 2 Super provides detailed reasoning outputs, including trajectory planning, chain-of-causation traces, and visual question answering with 2D grounding. These outputs link observations to actions, enabling developers to inspect, critique, and validate decisions. The model integrates with NVIDIA Halos safety-validation workflows and aligns with ISO/PAS 8800 requirements for AI safety engineering.

The model supports scene understanding, model critiquing, and knowledge distillation, allowing developers to use a single foundation model across the AV development stack. Alpamayo 2 Super can also function as an auto-labeler, transforming raw driving data into annotated training datasets within days, reducing annotation cycles from months to significantly shorter timeframes.

Original source → Deals on Clipraptor.com →