Norbert Klockiewicz

Mobile ML Engineer – on-device inference (React Native, ExecuTorch) | Open Source Contributor
@swmansion

[Norbert Klockiewicz @Nklockiewicz]

Not gonna lie, this one's impressive https://t.co/pDgZHT6yUp

[Norbert Klockiewicz @Nklockiewicz]

Watched the WWDC keynote. Lost count of how many times they said "on-device."

They know it's the way.

[Norbert Klockiewicz @Nklockiewicz]

There's no way they made Siri actually work.

[Software Mansion @swmansion]

Run pose estimation on-device in your React Native app! 🦾

RN ExecuTorch v0.9 has the usePoseEstimation hook that detects human bodies and maps keypoints.

See the demo and full release notes ⬇️

[Norbert Klockiewicz @Nklockiewicz]

@m090009 @swmansion 👀

[Norbert Klockiewicz @Nklockiewicz]

This guy is squeezing on-device speech to text to its limits.

[Igor Swat @igor_swat66626]

🌍 One prompt, many languages, all on-device.

We are shipping multilingual support in React Native ExecuTorch v0.9:
→ Gemma 4 generates the response
→ Kokoro TTS speaks it aloud
→ Everything runs locally on mobile 📱

Here's a quick demo 👇

[Norbert Klockiewicz @Nklockiewicz]

The first talk in public and right away on the big stage. Had a great time at @appjsconf

[Norbert Klockiewicz @Nklockiewicz]

Incredibly proud to share some knowledge in front of the best audience.

[App.js Conf 🗓️ 27-29 May 2026 @appjsconf]

Models designed to run on edge devices are gaining popularity, but using them poses challenges you may not see coming. 🤔

@Nklockiewicz is now sharing our experience from building ⁠react-native-executorch⁠ and shipping apps with on-device inference. This sounds like a talk you shouldn’t miss if you build with AI.

[Norbert Klockiewicz @Nklockiewicz]

@xenovacom That's actually crazy, can't imagine where we will be year.

[Norbert Klockiewicz @Nklockiewicz]

As always we are bringing some cool stuff to on device AI with React Native

[Software Mansion @swmansion]

With RN ExecuTorch 0.9.0, you can run @OpenAI's privacy filter to redact sensitive data, on-device! 🔒

What else is new?
➡️Pose estimation with YOLO – detect and track body keypoints in real time
➡️ FastSAM for promptable image segmentation – tap an object, get a mask
➡️ NPU-accelerated Whisper – up to 10x faster speech recognition on iOS

Watch the privacy filter demo and check out the full release notes! ⬇️

[Norbert Klockiewicz @Nklockiewicz]

Bro is a cat lover

[Bartek @_bartekOb]

I've always been a heavy user of iOS stickers - so I wondered how hard it'd be to build my own in React Native.
One hook, one model, a bit of Skia - that's the whole app and it's fully local too!

react-native-executorch 0.9 drops next week with FastSAM support 🚀🚀

[Norbert Klockiewicz @Nklockiewicz]

Quite a big deal ☺️ wonderful work from @mkopcins

[Google Gemma @googlegemma]

Gemma 🤝 React Native📱

Exciting news for mobile developers! We love seeing the community unlock new ways to build.

You'll soon be able to run Gemma 4 completely on-device in React Native.

[Software Mansion @swmansion]

On-device @googlegemma in React Native with react-native-executorch 🔥

Coming to the library very very soon!

@googleaidevs

[Norbert Klockiewicz @Nklockiewicz]

@SurajChawh79862 @DnuLkjkjh @OpenAI The weight of the model is actually after the quantization and it's the same as mlx one after 4 bit quantization. There's nothing to improve in that field.

[Norbert Klockiewicz @Nklockiewicz]

Just got @OpenAI's privacy filter model running on-device with react-native-executorch.

~600MB RAM, and the quality is genuinely impressive.
Imagine scanning an email before you send it to catch sensitive data — no cloud, no leaks. Tons of new on-device use cases unlocked.
Coming soon 👀

[Norbert Klockiewicz @Nklockiewicz]

Fine-tuned models are the most exciting part of running AI on-device. Yesterday I made the privacy filter model working in react-native-executorch. Today, support for a version fine-tuned on the Nemotron dataset -> 7x more entity types than the original. Both already running locally, still wrapping up the implementation. Release soon.
Great work from @MaziyarPanahi 👏

[Maziyar PANAHI @MaziyarPanahi]

Same text. Two privacy filters.

OpenAI's model catches 8 categories. OpenMed catches 55+: medical record numbers, blood type, API keys, financial codes, demographics.

Trained on Nemotron data by Nvidia. All on-device. All open-source.

Coming soon! What's missing?

[Norbert Klockiewicz @Nklockiewicz]

@Kaiyes_ @OpenAI whisper from openai
https://t.co/ooPuZ3khtG

[Norbert Klockiewicz @Nklockiewicz]

App size, by a mile. The model itself is ~750MB, which doesn't fit comfortably into any app bundle. Cold start and memory-after-repeated-scans were both fine in practice.
The realistic options are: ship it in the bundle and eat the download size, or fetch it in the background post-install with some UX around the first-run state. Both work, just different tradeoffs.

[Norbert Klockiewicz @Nklockiewicz]

That's neat — you can now build apps with real-time computer vision and test them on a simulator.

SimCam + react-native-executorch + vision camera v5 is such a powerful combo

[Software Mansion @swmansion]

Launching SimCam – a tool that finally lets you test camera features directly in the iOS simulator! 🚀

🎦 Stream video from your Mac's built-in or external camera, inject an image or video, or generate a QR code.

[Norbert Klockiewicz @Nklockiewicz]

@liquidai @MercedesBenz Congrats guys!