Skip to content

Recorded comparisons

Faster inference in action.

Compare baseline and ZETIC-optimized execution on the same hardware.

13 demos

Humanoid execution

Task completion

Jetson AGX Orin

7× higher task success rate

vs Python eager

9% 63%

π0.5

VLA

Jetson AGX Thor

9.7× faster

vs PyTorch eager

253.7 ms 26.08 ms

LingBot-VA

VLA

Jetson AGX Thor

7.2× faster

vs PyTorch reference

11.15 s 1.54 s

Sonata (PTv3)

Point-cloud segmentation

Jetson AGX Thor

23.1× faster

vs PyTorch FP32 · CPU voxelization

715 ms 31 ms

Isaac-0.2-2B + SAM2

Vision & tracking

Jetson Thor

10.5× faster · peak

vs TensorRT FP16 · full generation

3.16 s 0.30 s

Cosmos Policy

VLA

Jetson Thor

6.7× faster

vs As-released · skip-decode

1.83 s 275 ms

FoundationStereo

Stereo depth

Jetson AGX Thor

2.7× faster

vs PyTorch FP16

104 ms 38 ms

FoundationStereo · Three modes

Stereo depth

Jetson AGX Orin

3.6–8.6× faster

vs PyTorch reference

320 ms 37–89 ms

π0.5 · Orin

VLA

Jetson AGX Orin 64GB

2.8× faster

vs TensorRT FP16

215 ms 77 ms

Sonata (PTv3) · Orin

Point-cloud segmentation

Jetson AGX Orin

6.7× faster

vs FP32 · CPU voxelization

991 ms 149 ms

YOLO26m · 500 images

Object detection

Jetson AGX Orin

1.6× faster

vs TensorRT INT8 · detection head FP16

4.83 ms 2.99 ms

YOLO26m · 10-camera video

Object detection

Jetson AGX Orin

1.6× faster

vs TensorRT INT8 · detection head FP16

207 fps 335 fps

KEV-4B

Real-time decisions

Jetson AGX Thor

4.5× faster

vs PyTorch

59 ms 13 ms

Looking for Orin, Nano, or precision-specific benchmarks?

Explore ixian-bench

Get more tasks done.

Tell us about your model, hardware, and performance goals.

Your inquiry

Prefer email? contact@zetic.ai