Project AURIONAI Use-Cases Research & Innovation
driving

Alpamayo 1.5-10B

NVIDIA open driving VLA on a Cosmos-Reason2 backbone, RL post-trained; weights OpenMDW-1.1, code Apache 2.0.

NVIDIANVIDIAUSA
NVIDIA
Levelmodel
Classdriving
Parameters10B
Contextnot in the notes
Released19 Mar 2026
Opennessunknown
Runs onnot in the notes
Statusactive

Lineage

successorfinetune
Cosmos Reason 1 to Cosmos Reason 2: successor, medium confidenceCosmos Reason 2 to Alpamayo 1.5-10B: finetune, high confidenceCosmos Reason 1Cosmos Reason 1NVIDIACosmos Reason 2Cosmos Reason 2NVIDIA, Jan 2026Alpamayo 1.5-10BAlpamayo 1.5-10BNVIDIA, Mar 2026
NVIDIACosmos Reason 2 is the parent (finetune)high confidencemodel card
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 3 models. Confidence and evidence are the notes' own.

R&D Topics

End-to-end driving policies with reasoningproduced by

Runtimes

NVIDIA NIMnvidia

Identity

Developer
NVIDIA
Family
not in the notes
Released
19 Mar 2026 sourcesregistry date
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
hybrid Transformer VLA with diffusion trajectory decoder; 4 cameras, egomotion, text inputs; Chain-of-Causation reasoning plus 6.4 s, 64-waypoint trajectory
Total parameters
10B sources
Active parameters
–
Checkpoint parameters
–
Note
About 10B (8.2B backbone + 2.3B action expert)
Context length
not in the notes
Input
video, text, sensor
Output
action, text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
OpenMDW License v1.1 sources
Access routes
open weights download, API
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
NVIDIA NIM
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. Alpamayo-1.5-10B | NVIDIA NGC catalog.ngc.nvidia.com https://catalog.ngc.nvidia.com/orgs/nim/nvidia/models/alpamayo-1-5-10b/-

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Alpamayo 1.5-10B", https://aurion.semai.id/models/nvidia-alpamayo-1-5-10b/, records of October 2026.