SSyncDev

Alpamayo 2 Edge

SyncDev model directory · Profile updated Nov 18, 2026

Compare with another model

Alpamayo 2 Edge is NVIDIA's open 2B-class driving VLA that outputs trajectories with causal explanations, sized for DRIVE AGX Thor in-vehicle use.

Key specifications

Specification score
25.0
License
OpenMDW-1.1 (weights); Apache-2.0 (code)

The specification score summarizes recorded features and limits. It is not a benchmark result.

Pricing conditions: Open weights; no per-token price is published. Your cost is the GPU time you run it on.

Inputs and outputs

Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.

Accepts

  • Image input
  • Text input

Produces

  • Text output

Capabilities

ReasoningVisionOpen weights

What is Alpamayo 2 Edge?

Explainable planning has mostly been a datacentre luxury in autonomous driving. Alpamayo 2 Edge tries to put it in the car. It is a compact reasoning vision-language-action model that predicts where the vehicle should go and writes a Chain-of-Causation explanation of why, and it is meant to be fine-tuned and then deployed on NVIDIA DRIVE AGX Thor.

What goes in, what comes out

Trajectory prediction looks at six cameras across 22 frames: five each from the front wide and front tele cameras over the last two seconds, and three each from the four side and rear cameras. Add a text navigation instruction and 20 past ego poses at 0.1-second steps.

Out comes a trajectory of 64 waypoints covering 0.1 to 6.4 seconds, each with an XYZ position and a 3x3 rotation, plus reasoning text. Sample several candidates and each gets its own reasoning. The same model also answers free-form questions about a scene, using four frames per camera.

Parameter budget

Part Size
Language model (from Cosmos 3 Edge, Nemotron-based) 1.96B
SigLIP2 vision encoder 0.41B
Projector 0.08B
Diffusion action expert 0.2B

Weights are BF16 under OpenMDW-1.1. The code is Apache-2.0.

Things integrators trip over

  • The chat template turns thinking on by default. NVIDIA says to apply it with enable_thinking=False; the driving prompt supplies its own empty reasoning block.
  • Every frame needs a capture timestamp, because the prompt encodes relative-time labels.
  • The action expert predicts acceleration and curvature, integrated through a unicycle model. Yaw estimates the body heading, which differs from the path tangent by the training vehicle's rear-axle sideslip. Account for that before comparing against your own logs.

The repository dates from 12 August 2026, but NVIDIA lists 10 November 2026 as the public release.

Evaluating it on your fleet data

Replay logged drives with the camera layout remapped to the expected six IDs. Score open-loop displacement error at 1, 3 and 6 seconds, then have an engineer read fifty explanations for cases where the plan was wrong. An explanation that sounds right on a bad trajectory is the failure mode to look for. Only then consider closed-loop simulation.

It is part of NVIDIA's open platform for vehicles; related releases are on the NVIDIA provider page, and broader vision-language models are under multimodal.

How to evaluate Alpamayo 2 Edge

Compare the model on the work you need to complete.

Tasks and inputs

Alpamayo 2 Edge is listed for Image-text-to-text, Multimodal. It accepts image, text and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.

Capacity and cost

Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.

Choosing a deployment

The weights are downloadable under OpenMDW-1.1 (weights); Apache-2.0 (code). Check runtime support and size the complete model and working context for your expected concurrency.

Frequently asked questions

A 64-waypoint trajectory covering 0.1 to 6.4 seconds plus Chain-of-Causation reasoning text, or answers to free-form questions about a driving scene.

These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.

shanghai-ai-lab

Sage-SciPerception

Sage-SciPerception is Shanghai AI Lab's set of projectors feeding crystals, spectra, biological sequences and biosignals into a language model's input.

— context

inclusionAI

Ling 3.2 Flash

Ling 3.2 Flash is inclusionAI's 560B-A25B multimodal MoE with a 1M-token window, built for visual agents, 3D tasks and medical image reasoning.

1M context

Swiss AI

Apertus 1.5 8B

Apertus 1.5 8B is the Swiss AI Initiative's open multilingual model, now taking text, images and audio with a 262K-token context window.

262.14K context

kyutai

REKI-2B

REKI-2B is Kyutai's open 2.4B robot vision-language-action model with cheap register-token memory, pretrained only on public data.

— context

black-forest-labs

FLUX 3 Action

FLUX 3 Action is Black Forest Labs' open 7B world action model for robots, predicting action chunks and future video from cameras, state and text.

— context