NVIDIA Alpamayo
Vision-language-action models for self-driving vehicles: they plan a trajectory from camera video and explain the decision in text. Used to develop and test autopilot systems, not as a ready-made autopilot.
- Developer
- NVIDIA, USA
- First release
- Nov 2025
- Latest release
- Aug 2026
- Sizes
- 10B – 34B
- License
- Commercial use with conditionsWeights — OpenMDW 1.1, code — Apache 2.0; however, the Alpamayo 1 and 1.5 model cards state "for non-commercial use, commercial license on request"
- Russian
- Not supported
- Running
- On your own serverNeeds a GPU
- Industries
- Manufacturing and logistics, Science and research
What it does
- Auto-labeling camera recordings to train your own driver assistance systems
- Analyzing complex road scenes with text explanations
- Testing autopilot systems in simulation on rare scenarios
Where it is used
Hardware requirements
Versions
- Alpamayo 2 Super 34B
- Alpamayo 1.5 10B
- Alpamayo-R1 (Alpamayo 1) 10B
How to run it
I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.
Frequently asked questions
Can NVIDIA Alpamayo be used in a commercial project?
With conditions. License: Weights — OpenMDW 1.1, code — Apache 2.0; however, the Alpamayo 1 and 1.5 model cards state "for non-commercial use, commercial license on request". Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.
What hardware does NVIDIA Alpamayo need?
At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.
Does NVIDIA Alpamayo support Russian?
No. The model card lists its languages and Russian is not among them.
Where can I download NVIDIA Alpamayo and what does it cost?
The NVIDIA Alpamayo weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.
How I deploy it for clients
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
An autonomous driving model based on Qwen3.5-4B: 3D detection of objects around the vehicle, answers to questions about the road scene and trajectory planning in one model.
DetailsRoboticsNVIDIA CosmosNVIDIA · USACommercial use allowed"World" models for robots and self-driving vehicles: they generate realistic video of physical scenes and predict actions. Cosmos 3 combines understanding, generation and control.
DetailsAutonomous drivingcomma.ai openpilot (supercombo)comma.ai · USACommercial use allowedAn open driver assistance system: a neural network keeps the lane and controls speed from a camera, plus a driver attention monitoring model. The models live right in the repository and are updated constantly.
DetailsSource: huggingface.co/nvidia/Alpamayo-1.5-10B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


