π0.5 · Jetson AGX Thor · PyTorch reference baseline
16.8× faster policy inference
Policy inference · p50
Baseline: 714 msZETIC optimized: 42.5 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.
Packaged for ROS 2 integration.
Watch the differenceIsaac-0.2-2B + SAM2 · Jetson Thor · Original recording
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 optimized execution.
- Measurement
- Policy inference latency (p50): 714 ms → 42.5 ms. These values measure inference, not complete physical task duration.
- Recording
- LIBERO-Object simulation, 10 tasks. Recorded robot actions are replayed with each side's measured inference delay. Final replay times: 257.4 s → 77.4 s.
- 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. The recording also shows cumulative inference across four chunks: 44.60 s → 6.20 s.
- Recording
- RoboTwin beat_block_hammer replay, with the same task and seed. Robot holds reflect measured inference time.
- Playback
- 2× playback, as labeled in the original recording.
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. The recording also shows completion across 10 tasks: 176.2 s → 54.8 s. The task completion difference includes the planning-mode change.
- Recording
- LIBERO-Spatial simulation. Same 10 tasks, initial states, checkpoint, seed and 20 Hz control on both sides.
- Playback
- 1× opening, then 5× and 10× on both sides, as labeled. The optimized side holds its completed frame while the baseline continues.
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
- Instruction: “girl jumping on the bed”. The original coordinate output, segmentation masks and tracking are preserved.
- Playback
- 1× real-time playback.
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.
- A ROS 2 package and integration guidance
- 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.
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 comparisonWhat 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 the agreed workload, before/after measurements, and a ROS 2 package with integration guidance.
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