π0.5 · Jetson AGX Thor · PyTorch reference baseline
37.2× faster policy inference
Policy inference · p95
Baseline: 714 msZETIC optimized: 19.20 ms
The player could not load here. Open the video
Hardware-aware inference optimization
Faster AI.On your robot’shardware.
Execution design for faster inference.
Integrated into your existing stack.
The player could not load here.Open the video ↗
See faster robot executionπ0.5 · Jetson AGX Thor · Recorded comparison
Loading cooking demo…
The interactive scene couldn’t load.
Click an object to start.
Interactive demos are available on desktop.
Recorded comparisons
See what faster
execution looks like.
Compare baseline and optimized execution
on the same hardware.
Measurement details
- Model & hardware
- π0.5 · Jetson AGX Thor. Model by Physical Intelligence.
- Execution
- openpi PyTorch reference → ZETIC hardware-aware execution optimization.
- Measurement
- Policy inference latency (p95): 714 ms → 19.20 ms. These values measure inference, not complete physical task duration.
- Recording
- Simulated robot actions replayed with each side’s measured inference delay; this is not a live robot recording.
- Playback
- 1× until the optimized side completes the first task, then 5× and 10×, as labeled in the recording.
LingBot-VA · Jetson AGX Thor · PyTorch reference baseline
7.2× faster inference
Inference per action chunk
Baseline: 11.15 sZETIC optimized: 1.54 s
The player could not load here. Open the video
Measurement details
- Model & hardware
- LingBot-VA · Jetson AGX Thor. Model by Robbyant.
- Execution
- PyTorch reference → ZETIC optimized runtime.
- Measurement
- Inference per action chunk: 11.15 s → 1.54 s.
- Recording
- Simulated robot-task replay under matching conditions. Pauses reflect measured inference time.
- Playback
- 2× playback, as labeled.
Sonata (PTv3) · Jetson AGX Thor · Stock PyTorch baseline
23.1× faster point-cloud segmentation
End-to-end latency per frame
Baseline: 715 msZETIC optimized: 31 ms
The player could not load here. Open the video
Measurement details
- Model & hardware
- Sonata (PTv3) · Jetson AGX Thor · Point-cloud segmentation.
- Execution
- Stock PyTorch FP32 with CPU voxelization → ZETIC hardware-aware execution optimization.
- Measurement
- End-to-end latency per frame: 715 ms → 31 ms (23.1×). This includes the frame-processing pipeline, not just model inference.
- Recording
- 10 Hz sensor stream. Each side shows its latest completed result; frame counters and lag relative to the sensor are shown in the recording.
- Playback
- 1× playback, as labeled in the recording.
Isaac-0.2-2B + SAM2 · Jetson Thor · FP16 full-generation baseline
10.5× faster prompt response
Prompt response
Baseline: 3.16 sZETIC optimized: 0.30 s
The player could not load here. Open the video
Measurement details
- Model & hardware
- Isaac-0.2-2B + SAM2 · NVIDIA Jetson Thor · TensorRT backend.
- Execution
- Baseline: FP16 response generation completes before coordinate output. Optimized: FP8 response generation stops at coordinates; image understanding remains FP16.
- Measurement
- Instruction submission to completed target-coordinate output: 3.16 s → 0.30 s. This is prompt-response time, not time to first token.
- Recording
- The recording shows target selection, segmentation, and tracking following a text instruction.
- Playback
- 1× real-time playback.
Cosmos Policy · Jetson Thor · As-released, skip-decode baseline
6.7× faster action-chunk inference
Inference per 16-action chunk · p50
Baseline: 1.83 sZETIC optimized: 275 ms
The player could not load here. Open the video
Measurement details
- Model & hardware
- Cosmos Policy · Jetson Thor. Model by NVIDIA.
- Execution
- As-released Cosmos Policy with its official skip-decode flag → ZETIC optimized model and runtime. The baseline plans synchronously; the optimized run plans asynchronously.
- Measurement
- p50 inference latency per 16-action chunk: 1.83 s → 275 ms. Task-completion differences also include the change from synchronous to asynchronous planning.
- Recording
- Simulation of the same 10 tasks with matching model, starting conditions, and 20 Hz control.
- Playback
- 1× opening, then 5× and 10× on both sides, as labeled.
C-Fast-FoundationStereo · Jetson AGX Thor · Stock PyTorch baseline
2.7× faster stereo depth estimation
Latency per frame
Baseline: 104 msZETIC optimized: 38 ms
The player could not load here. Open the video
Measurement details
- Model & hardware
- C-Fast-FoundationStereo · Jetson AGX Thor.
- Execution
- Stock PyTorch FP16 → ZETIC hardware-aware execution optimization.
- Measurement
- Latency per frame: 104 ms → 38 ms (2.7×).
- Recording
- KITTI stereo frames replayed at 15 Hz, recorded at 10 Hz. Each side shows its latest completed depth map. The frame counters show skipped frames and lag relative to the camera stream.
- Playback
- 1× playback, as labeled in the recording.
Built around your workload.
Faster responses
Less time waiting for AI to understand, decide, and respond.
More from your hardware
Improve performance on your current board, or compare supported alternatives before buying.
Less optimization work
Measured results and an integration package, so your team can focus on the robot.
Execution design, handled by ZETIC
From your model
to an integration package.
You bring
Model + target hardware
Your performance and quality goals.
We handle
- Baseline measurement
- Execution design
- Validation & packaging
You receive
Your integration package.
- C/C++ library, ROS 2 package, or an integration tailored to your stack
- Optimized execution
- Before/after measurements
Two days
After the required inputs and scope are confirmed.For supported models and boards. New architectures and boards typically take about one week.
Built for your stack
- NVIDIA Jetson Thor, Orin, Nano
- Qualcomm QCS series, iQ series
Explore the benchmarks
Find the right model and hardware.
Explore how hardware, precision and execution change performance. Find the configuration that fits your workload.
Explore the benchmarks
Why ZETIC
The Edge Inference Company.
We bring AI into products that run on real hardware. Today, our focus is robotics and Physical AI, built on our work in mobile and embedded inference.
Customer experience
“We were impressed by the rapid compatibility validation across our target devices. The quality and reliability of the provided results were excellent.”
Programs & recognition
Before we get started
A few practical questions.
Can you improve a workload already using TensorRT?
Yes. TensorRT can remain the backend while ZETIC optimizes your workload. We agree on the execution path and delivery format for your application.
In our Isaac-0.2-2B + SAM2 demo on Jetson Thor, typical prompt-response time fell from ~1.5 s to 0.30 s — about 5× faster, with TensorRT retained.
Watch the TensorRT-based comparisonDo we need ROS 2?
No. ROS 2 is an optional packaging choice for teams that use it. We adapt delivery to your application’s runtime and integration requirements.
Can we integrate directly with a C/C++ application?
Yes. We can provide a C/C++ library for your application without a ROS 2 wrapper. The interface and dependencies are agreed during scoping.
What baseline do the demo speedups use?
Each demo names its reference baseline and measurement conditions. A speedup against PyTorch is not a speedup against TensorRT. For your project, we agree on a relevant baseline, including your tuned TensorRT implementation when applicable.
What do you need from us?
Your model, target hardware configuration, and performance and quality goals. We confirm the scope and any validation inputs needed before work starts.
What do we receive?
Optimized execution for your workload, before/after measurements, and integration into your runtime. Delivery can include a C/C++ library, ROS 2 package, or an integration tailored to your stack.
How long does it take?
For supported models and boards, two days after the required inputs and scope are confirmed. New architectures and boards typically take about one week.
Can you help us choose hardware?
Yes. We compare supported candidates against your workload’s performance and quality requirements, so you can evaluate the options before buying each board.
Start with your workload
Get faster inference
on your hardware.
Tell us what you’re building, the model you’re running, and where performance is holding you back.
We’ll review your model, hardware, and goals with you to define the scope.
contact@zetic.ai