TPSTokens Per Second

NVIDIA Alpamayo 2 Edge

NVIDIA🇺🇸 United States
active
Compare with other models →

Version History

2 Edgemajor

NVIDIA introduced Alpamayo 2 Edge, a 2B-parameter adaptive reasoning VLA model built on the Cosmos 3 Edge backbone for onboard use on DRIVE AGX Thor. It is post-trained with closed-loop RL in AlpaGym, which NVIDIA says improves closed-loop driving performance by 48.9% over the best checkpoint without closed-loop RL.

Coverage

model releaseNVIDIA

NVIDIA Alpamayo 2 Edge: 2B-Parameter Driving Model Hits 160-190 ms Latency on DRIVE AGX Thor

NVIDIA has introduced Alpamayo 2 Edge, a 2B-parameter adaptive reasoning vision-language-action model built for real-time operation on DRIVE AGX Thor. NVIDIA says deployment recipes with TensorRT and DFlash2 reach 160-190 ms pixel-to-trajectory latency, and that closed-loop RL improved driving performance by 48.9%.

3 min read
NVIDIAAlpamayo 2 Edgeautonomous vehicles