Loading video...

Video Failed to Load

Go Home

Before Fable 5 was shut down, it pushed Gemma 4 to 255 tok/s on WebGPU. Some didn't believe it was real. Today we're releasing the demo and kernels it wrote for you to see yourself. Run it locally in your browser. Agentic kernel optimization is the future of on-device inference

xenovacom's profile picture

Xenova

20,390 subscribers

483,425 views • 1 month 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 gave Fable 5 one job: write custom WebGPU kernels for Gemma 4 inference. It climbed to 84 tok/s, then hit a wall, insisting further optimization was impossible. Hours later, Anthropic rolled back invisible LLM development safeguards, and it hit 255 tok/s. The next day, access to Fable 5 was suspended globally.
0:35

I gave Fable 5 one job: write custom WebGPU kernels for Gemma 4 inference. It climbed to 84 tok/s, then hit a wall, insisting further optimization was impossible. Hours later, Anthropic rolled back invisible LLM development safeguards, and it hit 255 tok/s. The next day, access to Fable 5 was suspended globally.

Xenova

1,166,250 views • 2 months ago

Introducing SmolVLM 256M (& 500M): The world’s smallest multimodal model. Designed for efficiency and perfect for on-device applications! 🔥 It’s so small, it can even run 100% locally in your browser on WebGPU! 🤏 Powered by Transformers.js! ⚡️ Try it out yourself! 👇
0:26

Introducing SmolVLM 256M (& 500M): The world’s smallest multimodal model. Designed for efficiency and perfect for on-device applications! 🔥 It’s so small, it can even run 100% locally in your browser on WebGPU! 🤏 Powered by Transformers.js! ⚡️ Try it out yourself! 👇

Xenova

25,302 views • 1 year ago

NEW: Google releases Gemma 4, their most capable open models yet! 🤯 Apache-2.0, multimodal (text, image, and audio input), and multilingual (140 languages)! They can even run 100% locally in your browser on WebGPU. Watch it describe the Artemis II launch! 🚀 Try the demo! 👇
1:35

NEW: Google releases Gemma 4, their most capable open models yet! 🤯 Apache-2.0, multimodal (text, image, and audio input), and multilingual (140 languages)! They can even run 100% locally in your browser on WebGPU. Watch it describe the Artemis II launch! 🚀 Try the demo! 👇

Xenova

38,427 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

117,708 views • 2 years ago

Bonsai 27B just changed the local LLM game forever. 1-bit quantization shrinks it from 54GB to just 3.8GB (-93%), while retaining 90% of its intelligence. That's insane. With custom WebGPU kernels written by Fable 5 and GPT 5.6 Sol, the model now runs locally in your browser!
1:29

Bonsai 27B just changed the local LLM game forever. 1-bit quantization shrinks it from 54GB to just 3.8GB (-93%), while retaining 90% of its intelligence. That's insane. With custom WebGPU kernels written by Fable 5 and GPT 5.6 Sol, the model now runs locally in your browser!

Xenova

209,397 views • 29 days ago

you don’t need a robot to see physical ai in action, you just need a browser. this week I finally tried something I've wanted to do for a while: design an SO-101 scene in three.js, connect it to a real leader arm, collect teleoperation data, train an ACT model, then port it to run in the browser. the result is the first ever demo of ACT that runs locally on the web. try it yourself now at
0:35

you don’t need a robot to see physical ai in action, you just need a browser. this week I finally tried something I've wanted to do for a while: design an SO-101 scene in three.js, connect it to a real leader arm, collect teleoperation data, train an ACT model, then port it to run in the browser. the result is the first ever demo of ACT that runs locally on the web. try it yourself now at

Binh Pham

121,383 views • 1 month ago

NEW: LiquidAI just released LFM2.5-350M, a tiny model that brings agentic AI and tool-calling capabilities to resource-constrained environments. 🤯 It can even run locally in your browser via WebGPU, serving as a powerful companion while you browse the web. Try the demo! 👇
0:29

NEW: LiquidAI just released LFM2.5-350M, a tiny model that brings agentic AI and tool-calling capabilities to resource-constrained environments. 🤯 It can even run locally in your browser via WebGPU, serving as a powerful companion while you browse the web. Try the demo! 👇

Xenova

26,267 views • 4 months ago

Really excited to share TeXPen! It converts your handwriting and screenshots directly into LaTeX. It is buit to run entirely in your browser using WebGPU/WebAssembly. It was a fun challenge getting the models to run client-side, but it means zero latency and total privacy.
1:48

Really excited to share TeXPen! It converts your handwriting and screenshots directly into LaTeX. It is buit to run entirely in your browser using WebGPU/WebAssembly. It was a fun challenge getting the models to run client-side, but it means zero latency and total privacy.

Ji-Ha

147,492 views • 8 months ago

Gemma 4 can run on phones without an internet connection! 🤯 It can perform local agentic tasks, such as logging and analyzing trends. When connected, it can also make API calls. Want to try it yourself? Get the Google AI Edge App on iOS or Android. (🔊 Sound on for the demo!)
2:44

Gemma 4 can run on phones without an internet connection! 🤯 It can perform local agentic tasks, such as logging and analyzing trends. When connected, it can also make API calls. Want to try it yourself? Get the Google AI Edge App on iOS or Android. (🔊 Sound on for the demo!)

Google Gemma

759,305 views • 4 months ago

Day 3 of 5 building with Claude Fable 5 before it goes paid. Today: an audit of everything you have already made. 1. Fable 5 reads back through all your past Claude chats 2. It flags what worked, what you dropped, and where value is going to waste 3. It ranks the top 10 fixes by effort against impact 4. Then it hands you a concrete plan for the top 3 5. Run that plan on a cheaper model and save Fable 5 for the thinking Comment FABLE for the full guide. Make sure you follow me so I can DM it to you. Day 4 tomorrow.
0:52

Day 3 of 5 building with Claude Fable 5 before it goes paid. Today: an audit of everything you have already made. 1. Fable 5 reads back through all your past Claude chats 2. It flags what worked, what you dropped, and where value is going to waste 3. It ranks the top 10 fixes by effort against impact 4. Then it hands you a concrete plan for the top 3 5. Run that plan on a cheaper model and save Fable 5 for the thinking Comment FABLE for the full guide. Make sure you follow me so I can DM it to you. Day 4 tomorrow.

Charlie Hills

13,617 views • 1 month ago

Is this the future of AI browser agents? 👀 WebGPU-accelerated reasoning LLMs are now supported in Transformers.js! 🤯 Here's MiniThinky-v2 (1B) running 100% locally in the browser at ~60 tps (no API calls)! I can't wait to see what you build with it! Demo + source code in 🧵👇
0:22

Is this the future of AI browser agents? 👀 WebGPU-accelerated reasoning LLMs are now supported in Transformers.js! 🤯 Here's MiniThinky-v2 (1B) running 100% locally in the browser at ~60 tps (no API calls)! I can't wait to see what you build with it! Demo + source code in 🧵👇

Xenova

81,477 views • 1 year 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

Sam Altman says the goal is to run a GPT-5 quality model locally on a single device We don't know how to do it yet, but the recent efficiency gains were also once thought impossible The vision is a new computer form factor for the AI era: "it should run locally... if you want it to"
0:47

Sam Altman says the goal is to run a GPT-5 quality model locally on a single device We don't know how to do it yet, but the recent efficiency gains were also once thought impossible The vision is a new computer form factor for the AI era: "it should run locally... if you want it to"

Haider.

197,384 views • 8 months ago

GEMMA 4 IS STARTING TO KILL A LOT OF AI SUBSCRIPTIONS. Local inference, multimodal support, strong coding, and no API bill is making “just run it on your own machine” feel way more real.
9:24

GEMMA 4 IS STARTING TO KILL A LOT OF AI SUBSCRIPTIONS. Local inference, multimodal support, strong coding, and no API bill is making “just run it on your own machine” feel way more real.

0xMarioNawfal

65,679 views • 4 months ago

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯 It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW! Demo (+ source code) 👇
1:05

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯 It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW! Demo (+ source code) 👇

Xenova

88,762 views • 2 years ago

What does it take to run 3, 5, or even 10 concurrent instances of Gemma 4 locally? We've open-sourced a demo letting you run multiple models side-by-side on your hardware. Gemma 4 26B A4B easily runs 10+ concurrent requests on a MacBook Pro M4 Max at 18 tokens/sec per request.
0:48

What does it take to run 3, 5, or even 10 concurrent instances of Gemma 4 locally? We've open-sourced a demo letting you run multiple models side-by-side on your hardware. Gemma 4 26B A4B easily runs 10+ concurrent requests on a MacBook Pro M4 Max at 18 tokens/sec per request.

Google Gemma

913,765 views • 3 months ago

The dominant story in AI has been the growing cloud: bigger clusters, larger models, more gigawatts. We believe the future is in the opposite direction: on-device inference, smaller models, watts instead of gigawatts. Today we're releasing OpenJarvis v1.0: a personal AI assistant that lives, learns, and works on your device.
1:13

The dominant story in AI has been the growing cloud: bigger clusters, larger models, more gigawatts. We believe the future is in the opposite direction: on-device inference, smaller models, watts instead of gigawatts. Today we're releasing OpenJarvis v1.0: a personal AI assistant that lives, learns, and works on your device.

Jon Saad-Falcon

157,311 views • 2 months ago

Gemma 2 2B running in a browser, powered by WebLLM & WebGPU! 🔥 100% local & on-device In less than 24 hours, we've already got the model to the edge! ⚡ Try it out on an HF space below:
1:31

Gemma 2 2B running in a browser, powered by WebLLM & WebGPU! 🔥 100% local & on-device In less than 24 hours, we've already got the model to the edge! ⚡ Try it out on an HF space below:

Vaibhav (VB) Srivastav

53,790 views • 2 years ago

It's here: We just hit superhuman performance on AI kernel optimization! Real customer models & production settings. Not toy problems (what I typically see). This is the year that Claude writes its own kernels, Codex its own kernels, for every new GPU that it wants to run on -- something that takes months to port between GPU generations today. This has a massive impact to scaling intelligence. More compute means getting the next frontier model sooner.
2:48

It's here: We just hit superhuman performance on AI kernel optimization! Real customer models & production settings. Not toy problems (what I typically see). This is the year that Claude writes its own kernels, Codex its own kernels, for every new GPU that it wants to run on -- something that takes months to port between GPU generations today. This has a massive impact to scaling intelligence. More compute means getting the next frontier model sooner.

Sharon Zhou

241,935 views • 5 months ago

Gavin explains that the bear case for AI capex spend is on-device inference: "In three years, on a bigger phone, you'll be able to run a pruned-down version of Gemini 5, Grok 4, or ChatGPT. And that's free. This is clearly Apple's strategy - we're going to make it privacy-safe and run on the phone. Other than scaling laws breaking, edge AI is by far the most plausible and scariest bear case."
1:20

Gavin explains that the bear case for AI capex spend is on-device inference: "In three years, on a bigger phone, you'll be able to run a pruned-down version of Gemini 5, Grok 4, or ChatGPT. And that's free. This is clearly Apple's strategy - we're going to make it privacy-safe and run on the phone. Other than scaling laws breaking, edge AI is by far the most plausible and scariest bear case."

Patrick OShaughnessy

517,362 views • 8 months ago