model releaseNVIDIA

NVIDIA Releases Alpamayo 2 Edge, a 2B-Class Reasoning VLA Running on DRIVE AGX Thor at 160 to 190 ms

TL;DR

NVIDIA released Alpamayo 2 Edge, a 2B-class reasoning vision-language-action (VLA) model that plans driving trajectories and explains them. It runs on DRIVE AGX Thor at 160 to 190 ms pixel-to-trajectory latency, according to MarkTechPost.

1 min read
0

NVIDIA has released Alpamayo 2 Edge, a 2B-class reasoning vision-language-action (VLA) model that plans driving trajectories and explains them on DRIVE AGX Thor. MarkTechPost reports pixel-to-trajectory latency of 160 to 190 ms.

Key facts

  • Model: Alpamayo 2 Edge
  • Developer: NVIDIA
  • Size: 2B-class parameters
  • Type: Reasoning vision-language-action model
  • Function: Plans driving trajectories and explains them
  • Hardware: DRIVE AGX Thor
  • Latency: 160 to 190 ms, pixel to trajectory

What this means

Alpamayo 2 Edge pairs trajectory planning with explanations in a single model, and its 2B-class size is paired with a reported 160 to 190 ms pixel-to-trajectory latency on DRIVE AGX Thor.

Related Articles

Comments

Loading...

NVIDIA Alpamayo 2 Edge: 2B Reasoning VLA for DRIVE Thor | TPS