Loading video...

Video Failed to Load

Go Home

WebGPU inference might be the most underrated tech in AI right now. This entire audiobook was generated in the browser on my M1 MacBook Pro. - Kokoro 82M for TTS - Whisper Base for transcription/captions It runs so fast with WebGPU that most people won't even realize it's happening...

konstipaulus's profile picture

konstantinpaulus

5,864 subscribers

63,248 views • 10 months ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I got WebGPU support working so now my dumb little social MMO game runs fully in the browser (and on Newgrounds hopefully)
0:48

I got WebGPU support working so now my dumb little social MMO game runs fully in the browser (and on Newgrounds hopefully)

chip

231,917 views • 29 days ago

We've been partnering with Unity for Games to bring WebGPU to their engine, so their developers have everything they need to build immersive games in the browser. Learn more about WebGPU in Unity → Get started with WebGPU →
0:57

We've been partnering with Unity for Games to bring WebGPU to their engine, so their developers have everything they need to build immersive games in the browser. Learn more about WebGPU in Unity → Get started with WebGPU →

Chrome for Developers

18,190 views • 2 years ago

Introducing Voxtral WebGPU: Real-time speech transcription entirely in your browser. This demo runs Voxtral-Mini-4B, a powerful streaming ASR model from Mistral AI, locally on WebGPU. The model supports 13 languages and is capable of <500 ms latency. Fully private. Zero cost.
0:39

Introducing Voxtral WebGPU: Real-time speech transcription entirely in your browser. This demo runs Voxtral-Mini-4B, a powerful streaming ASR model from Mistral AI, locally on WebGPU. The model supports 13 languages and is capable of <500 ms latency. Fully private. Zero cost.

Xenova

94,356 views • 4 months ago

Made some major improvements to my WebGPU water shader (thanks Ghislain Girardot for the feedback!) Fixed a bug where waves weren't propagating and implemented JONSWAP spectrum for more realistic wave grouping. Hitting ~70FPS @ 2K res on my Macbook M1 Pro #threejs #webgpu #shaders
0:44

Made some major improvements to my WebGPU water shader (thanks Ghislain Girardot for the feedback!) Fixed a bug where waves weren't propagating and implemented JONSWAP spectrum for more realistic wave grouping. Hitting ~70FPS @ 2K res on my Macbook M1 Pro #threejs #webgpu #shaders

Dan Greenheck

18,852 views • 7 months ago

Introducing TTS WebGPU: The first ever text-to-speech web app built with WebGPU acceleration! 🔥 High-quality and natural speech generation that runs 100% locally in your browser, powered by OuteTTS and Transformers.js.🤗 Try it out yourself! Demo + source code below 👇
0:32

Introducing TTS WebGPU: The first ever text-to-speech web app built with WebGPU acceleration! 🔥 High-quality and natural speech generation that runs 100% locally in your browser, powered by OuteTTS and Transformers.js.🤗 Try it out yourself! Demo + source code below 👇

Xenova

19,666 views • 1 year ago

Numbers in! Target: 150 tok/s browser-native Qwen 3.5 inference Achieved: 180 tok/s — Qwen 3.5 INT4, WebGPU, browser-only. No cloud, APIs, servers, just Pure WebGPU + WGSL optimizations, HF SafeTensors, single browser tab. Open AI, for real.
0:57

Numbers in! Target: 150 tok/s browser-native Qwen 3.5 inference Achieved: 180 tok/s — Qwen 3.5 INT4, WebGPU, browser-only. No cloud, APIs, servers, just Pure WebGPU + WGSL optimizations, HF SafeTensors, single browser tab. Open AI, for real.

Eric

256,656 views • 4 months ago

Introducing Phi-3 WebGPU, a private and powerful AI chatbot that runs locally in your browser, powered by 🤗 Transformers.js and onnxruntime-web! 🔒 On-device inference: no data sent to a server ⚡️ WebGPU-accelerated (> 20 t/s) 📥 Model downloaded once and cached Try it out! 👇
1:26

Introducing Phi-3 WebGPU, a private and powerful AI chatbot that runs locally in your browser, powered by 🤗 Transformers.js and onnxruntime-web! 🔒 On-device inference: no data sent to a server ⚡️ WebGPU-accelerated (> 20 t/s) 📥 Model downloaded once and cached Try it out! 👇

Xenova

117,690 views • 2 years ago

STOP SCROLLING!!! THIS MIGHT BE THE MOST UNDERRATED OPPORTUNITY ON THE INTERNET RIGHT NOW. I’M PUTTING $1M INTO AN AI AGENT SCHOLARSHIP. 200 PEOPLE WILL GET IN. $0 COST. NO TECH SKILLS NEEDED. If you’ve been waiting for a chance to get into AI, this is it. Learn. Build. Get ahead early. Apply now:
0:59

STOP SCROLLING!!! THIS MIGHT BE THE MOST UNDERRATED OPPORTUNITY ON THE INTERNET RIGHT NOW. I’M PUTTING $1M INTO AN AI AGENT SCHOLARSHIP. 200 PEOPLE WILL GET IN. $0 COST. NO TECH SKILLS NEEDED. If you’ve been waiting for a chance to get into AI, this is it. Learn. Build. Get ahead early. Apply now:

Evan Luthra

43,516 views • 3 months ago

WebGPU + Compute Shaders = 🤯 &gt;500K stars runs at 60fps on my M1 Pro ⚡️ In my latest blog post, I walk through how to build this interactive galaxy simulation 🌌 Source code and live demo link in comments 👇🏻 #threejs #webgl #webgpu #shaders
0:46

WebGPU + Compute Shaders = 🤯 &gt;500K stars runs at 60fps on my M1 Pro ⚡️ In my latest blog post, I walk through how to build this interactive galaxy simulation 🌌 Source code and live demo link in comments 👇🏻 #threejs #webgl #webgpu #shaders

Dan Greenheck

18,538 views • 7 months ago

Quest Browser 146.o now ships with experimental support for WebGPU in #WebXR. Turn on "webXR experimental features" in "chrome://flags" and the API will be available. Feedback welcome!
0:34

Quest Browser 146.o now ships with experimental support for WebGPU in #WebXR. Turn on "webXR experimental features" in "chrome://flags" and the API will be available. Feedback welcome!

@[email protected]

18,258 views • 2 months ago

Neural motion synthesis in Threejs/WebGPU, even runs on my 7y old Iphone! try it here: sauce:
0:20

Neural motion synthesis in Threejs/WebGPU, even runs on my 7y old Iphone! try it here: sauce:

Erik

106,992 views • 2 months ago

Said i'd release it this week. Here it is. Runs on webgpu, silky smooth, fast and in your browser. No signup, no subscription, no one time payment. Free forever. Link below
0:24

Said i'd release it this week. Here it is. Runs on webgpu, silky smooth, fast and in your browser. No signup, no subscription, no one time payment. Free forever. Link below

Alim

365,021 views • 5 months ago

Excited to announce that Three.js Water Pro 🌊 is now available for purchase! Can't wait to see what people build with this. Welcome to the era of WebGPU! 🚀 #threejs #webgpu #webgl #shaders
0:51

Excited to announce that Three.js Water Pro 🌊 is now available for purchase! Can't wait to see what people build with this. Welcome to the era of WebGPU! 🚀 #threejs #webgpu #webgl #shaders

Dan Greenheck

37,142 views • 5 months ago

Introducing Kokoro.js, a new JavaScript library for running Kokoro TTS, an 82 million parameter text-to-speech model, 100% locally in the browser w/ WASM. Powered by 🤗 Transformers.js. WebGPU support coming soon! 👉 npm i kokoro-js 👈 Link to demo (+ sample code) in 🧵
0:43

Introducing Kokoro.js, a new JavaScript library for running Kokoro TTS, an 82 million parameter text-to-speech model, 100% locally in the browser w/ WASM. Powered by 🤗 Transformers.js. WebGPU support coming soon! 👉 npm i kokoro-js 👈 Link to demo (+ sample code) in 🧵

Xenova

40,340 views • 1 year ago

Ok, I've decided to implement Particle Life simulation on GPU, using WebGPU, in browser. For now I've spawned 1'000'000 particles and implemented basic rendering &amp; camera movement. I recon computing interaction forces will be the most painful part to implement...
0:20

Ok, I've decided to implement Particle Life simulation on GPU, using WebGPU, in browser. For now I've spawned 1'000'000 particles and implemented basic rendering &amp; camera movement. I recon computing interaction forces will be the most painful part to implement...

Nikita Lisitsa

16,249 views • 1 year ago

made an interactive video model trained on tap-conditioned data.. tap the screen and it generates the next frames in realtime (small enough to run in the browser with webgpu, even on iphone)
0:24

made an interactive video model trained on tap-conditioned data.. tap the screen and it generates the next frames in realtime (small enough to run in the browser with webgpu, even on iphone)

sahir

23,151 views • 3 months ago

Qwen-2.5 on WebGPU 🏎️ • 42 tok/sec for Qwen2.5-Coder-1.5B on Mac ⚡ • Powered by MLC WebLLM and WebGPU 🔥 Watch Qwen2.5-Coder-1.5B build a website entirely in the browser!
0:35

Qwen-2.5 on WebGPU 🏎️ • 42 tok/sec for Qwen2.5-Coder-1.5B on Mac ⚡ • Powered by MLC WebLLM and WebGPU 🔥 Watch Qwen2.5-Coder-1.5B build a website entirely in the browser!

Caleb

41,579 views • 1 year ago

Real-time video captioning in your browser with @LiquidAI's LFM2-VL model on WebGPU. Sending every frame to a server was never going to be the answer. Imagine the bandwidth, latency and cost. Local inference. No server costs. Infinitely scalable. This is the way.
0:45

Real-time video captioning in your browser with @LiquidAI's LFM2-VL model on WebGPU. Sending every frame to a server was never going to be the answer. Imagine the bandwidth, latency and cost. Local inference. No server costs. Infinitely scalable. This is the way.

Xenova

48,682 views • 4 months ago

The Unreal Engine 5 Lyra sample now runs in WebGPU. Live link coming soon, stay tuned! #WebGPU #UnrealEngine5
0:41

The Unreal Engine 5 Lyra sample now runs in WebGPU. Live link coming soon, stay tuned! #WebGPU #UnrealEngine5

Alex St. Louis

38,485 views • 2 years ago