Alpamayo-1.5-10B

Alpamayo 1.5 Alpamayo** | **Code** Model Overview Description: Alpamayo 1.5 is a significant update to NVIDIA’s open 10B-parameter chain-of-thought reasoning VLA model, designed to be an interactive and steerable reasoning engine for the AV community. Alpamayo 1.5 is built on the Cosmos-Reason2 VLM backbone, is RL post-trained, and introduces support for navigation guidance, flexible camera counts, and user question answering. This model is ready for non-commercial use. Commercial licensing available upon request. License: The model weights are released under a non-commercial license. The inference code is released under the Apache 2.0 license. Deployment Geography: Global Use Case: Researchers and autonomous-driving practitioners who are developing and evaluating VLA models for autonomous-driving scenarios, particularly for handling rare, long-tail events. Release Date: Hugging Face 03/19/2026 via https://huggingface.co/nvidia/Alpamayo-1.5-10B Inference Code: GitHub: https://github.com/NVlabs/alpamayo1.5 Model Architecture: Architecture Type:** Transformer Network Architecture:** A VLA model based on Cosmos-Reason2 and featuring a diffusion-based trajectory decoder. This model was developed based on:** Cosmos-Reason2 (VLM backbone) with a diffusion-based action decoder Number of model parameters:** Backbone: 8.2B parameters Action Expert: 2.3B parameters Input(s): Input Type(s):** Image/Video, Text, Egomotion History Input Format(s):** Image: Red, Green, Blue (RGB) Text: String Egomotion History: Floating-point values `(x, y, z), R_rot` Input Parameters:** Image: Two-dimensional (2D), multi-camera, multi-timestep Text: One-dimensional (1D) Egomotion History: Three-dimensional (3D) translation and nine-dimensional (9D, 3x3) rotation, multi-timestep Other Properties Related to Input:** Multi-camera images (4 cameras by default: front-wide, front-tele, cross-left, cross-right) with 0.4 second history window at 10Hz (4 frames per camera), image resolution 1080x1920 pix