Xenova's banner
Xenova's profile picture

Xenova

@xenovacom • 20,786 subscribers

Bringing the power of machine learning to the web. Currently working on Transformers.js (@huggingface 🤗)

Shorts

There has been a huge debate recently about the best approach for image background removal. Here's my attempt: - In-browser inference w/ 🤗 Transformers.js - WebGPU accelerated (fast!) - Costs $0 (no image hosting or server processing) - No data leaves your device (privacy!)

There has been a huge debate recently about the best approach for image background removal. Here's my attempt: - In-browser inference w/ 🤗 Transformers.js - WebGPU accelerated (fast!) - Costs $0 (no image hosting or server processing) - No data leaves your device (privacy!)

419,172 views

You don't need Jev for good emoji search... just a tiny local model! Love this demo by Max Leiter, powered by a 33M-parameter embedding model running entirely in your browser (for free) with 🤗 Transformers.js!

You don't need Jev for good emoji search... just a tiny local model! Love this demo by Max Leiter, powered by a 33M-parameter embedding model running entirely in your browser (for free) with 🤗 Transformers.js!

13,450 views

Opus 4.7 just wrote a custom WebGPU kernel that runs Qwen3.5 up to 13x faster using a fused LinearAttention op! 🤯 Agentic kernel optimization is the future. Now live in 🤗 Transformers.js v4.2.0! P.S. I've updated all our previous demos to use this new version. Enjoy!

Opus 4.7 just wrote a custom WebGPU kernel that runs Qwen3.5 up to 13x faster using a fused LinearAttention op! 🤯 Agentic kernel optimization is the future. Now live in 🤗 Transformers.js v4.2.0! P.S. I've updated all our previous demos to use this new version. Enjoy!

78,510 views

Introducing 🤗 Transformers.js v4: state-of-the-art machine learning for the web! 🚀 New WebGPU backend (browser, Node.js, Bun, Deno) ⚡️ Huge performance improvements 🤯 Support for over 200 architectures 🛠️ Complete codebase refactor Learn more about our biggest release yet! 👇

Introducing 🤗 Transformers.js v4: state-of-the-art machine learning for the web! 🚀 New WebGPU backend (browser, Node.js, Bun, Deno) ⚡️ Huge performance improvements 🤯 Support for over 200 architectures 🛠️ Complete codebase refactor Learn more about our biggest release yet! 👇

81,237 views

Run OpenAI's new Whisper Turbo model 100% locally in your browser with Transformers.js! ⚡️ Transcribe 2 minutes of audio in ~12 seconds! 🤯 Demo + source code 👇

Run OpenAI's new Whisper Turbo model 100% locally in your browser with Transformers.js! ⚡️ Transcribe 2 minutes of audio in ~12 seconds! 🤯 Demo + source code 👇

138,406 views

Inspired by Andrej Karpathy's microgpt, I built microgpt.js: a JavaScript port that runs entirely in your browser! It's an exact numerical implementation, so the randomness and outputs match bit-for-bit! Try it out yourself and train your own GPT by simply opening a webpage! 👇

Inspired by Andrej Karpathy's microgpt, I built microgpt.js: a JavaScript port that runs entirely in your browser! It's an exact numerical implementation, so the randomness and outputs match bit-for-bit! Try it out yourself and train your own GPT by simply opening a webpage! 👇

48,392 views

Meta's Segment Anything Model (SAM) can now run in your browser w/ WebGPU (+ fp16), meaning up to 8x faster image encoding (10s → 1.25s)! 🤯⚡️ Video is not sped up! Everything runs 100% locally thanks to 🤗 Transformers.js and onnxruntime-web! 🔗 Demo:

Meta's Segment Anything Model (SAM) can now run in your browser w/ WebGPU (+ fp16), meaning up to 8x faster image encoding (10s → 1.25s)! 🤯⚡️ Video is not sped up! Everything runs 100% locally thanks to 🤗 Transformers.js and onnxruntime-web! 🔗 Demo:

120,432 views

I'm excited to announce that Transformers.js V3 is finally available on NPM! 🔥 State-of-the-art Machine Learning for the web, now with WebGPU support! 🤯⚡️ Install it from NPM with: 𝚗𝚙𝚖 𝚒 @𝚑𝚞𝚐𝚐𝚒𝚗𝚐𝚏𝚊𝚌𝚎/𝚝𝚛𝚊𝚗𝚜𝚏𝚘𝚛𝚖𝚎𝚛𝚜 or via CDN (example below) 👇

I'm excited to announce that Transformers.js V3 is finally available on NPM! 🔥 State-of-the-art Machine Learning for the web, now with WebGPU support! 🤯⚡️ Install it from NPM with: 𝚗𝚙𝚖 𝚒 @𝚑𝚞𝚐𝚐𝚒𝚗𝚐𝚏𝚊𝚌𝚎/𝚝𝚛𝚊𝚗𝚜𝚏𝚘𝚛𝚖𝚎𝚛𝚜 or via CDN (example below) 👇

87,392 views

New Andrej Karpathy video just dropped! 😍🔥 After watching, if you want to learn more about how different models (e.g., GPT4, Llama, T5, BERT) tokenize text, check out "The Tokenizer Playground": a web-app I built a few months ago with 🤗 Transformers.js! 🔗

New Andrej Karpathy video just dropped! 😍🔥 After watching, if you want to learn more about how different models (e.g., GPT4, Llama, T5, BERT) tokenize text, check out "The Tokenizer Playground": a web-app I built a few months ago with 🤗 Transformers.js! 🔗

76,227 views

IBM just released Granite 4.0 1B Speech, a compact and efficient speech-language model, designed for multilingual speech recognition and bidirectional speech translation. New #1 on the OpenASR leaderboard! It can even run in your browser on WebGPU, thanks to 🤗 Transformers.js

IBM just released Granite 4.0 1B Speech, a compact and efficient speech-language model, designed for multilingual speech recognition and bidirectional speech translation. New #1 on the OpenASR leaderboard! It can even run in your browser on WebGPU, thanks to 🤗 Transformers.js

21,506 views

WOW! 🤯 Language models are becoming smaller and more capable than ever! Here's SmolLM2 running 100% locally in-browser w/ WebGPU on a 6-year-old GPU. Look at that speed! ⚡️😍 Powered by 🤗 Transformers.js and ONNX Runtime Web! How many tokens/second do you get? Let me know! 👇

WOW! 🤯 Language models are becoming smaller and more capable than ever! Here's SmolLM2 running 100% locally in-browser w/ WebGPU on a 6-year-old GPU. Look at that speed! ⚡️😍 Powered by 🤗 Transformers.js and ONNX Runtime Web! How many tokens/second do you get? Let me know! 👇

12,557 views

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

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
xenovacom's profile picture

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

1,168,664 views • 4 months ago

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
0:57
xenovacom's profile picture

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

Xenova

485,900 views • 4 months ago

Simulating a fruit fly's neural network using custom WebGPU kernels, running locally in a browser. The demo uses real connectivity data for 166,700 neurons from the MaleCNS connectome. Paint neurons and watch their activity drive the fly's movements. Built with GPT-6 Astra.
1:13
xenovacom's profile picture

Simulating a fruit fly's neural network using custom WebGPU kernels, running locally in a browser. The demo uses real connectivity data for 166,700 neurons from the MaleCNS connectome. Paint neurons and watch their activity drive the fly's movements. Built with GPT-6 Astra.

Xenova

158,621 views • 1 month ago

It's official: Qwen3.8-27B just scored 52 on the Artificial Analysis Intelligence Index. We now have an open-weight model that matches GPT-5.6 Luna (max) AND can run locally... even in your browser with custom WebGPU kernels! What a time to be alive! 🤯
0:58
xenovacom's profile picture

It's official: Qwen3.8-27B just scored 52 on the Artificial Analysis Intelligence Index. We now have an open-weight model that matches GPT-5.6 Luna (max) AND can run locally... even in your browser with custom WebGPU kernels! What a time to be alive! 🤯

Xenova

188,212 views • 2 months 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
xenovacom's profile picture

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

211,255 views • 3 months ago

While we eagerly await Fable 5's return, our agentic WebGPU kernel optimization framework kept running. Opus 4.8 picked up where Fable left off, pushing Liquid AI's new LFM2.5 230M to an unbelievable 1,400 tok/s... running locally in your browser. Don't blink or you'll miss it.
0:57
xenovacom's profile picture

While we eagerly await Fable 5's return, our agentic WebGPU kernel optimization framework kept running. Opus 4.8 picked up where Fable left off, pushing Liquid AI's new LFM2.5 230M to an unbelievable 1,400 tok/s... running locally in your browser. Don't blink or you'll miss it.

Xenova

175,295 views • 3 months ago

Behold... GPT-OSS (20B) running 100% locally in your browser on WebGPU. This shouldn't be possible — but with Transformers.js v4 and ONNX Runtime Web, it is! A new class of AI apps is emerging. Zero-install, infinite distribution. Simply visit a website and run models locally.
1:23
xenovacom's profile picture

Behold... GPT-OSS (20B) running 100% locally in your browser on WebGPU. This shouldn't be possible — but with Transformers.js v4 and ONNX Runtime Web, it is! A new class of AI apps is emerging. Zero-install, infinite distribution. Simply visit a website and run models locally.

Xenova

311,512 views • 8 months ago

WTF?! This changes image generation forever! 🤯 PrismML just released Binary and Ternary Bonsai Image 4B! That's right, 1-bit diffusion models are here. Only ~3GB in size (FLUX.2 Klein 4B is 16GB). The most shocking part? It can run 100% locally in your browser. Try it now! 👇
0:37
xenovacom's profile picture

WTF?! This changes image generation forever! 🤯 PrismML just released Binary and Ternary Bonsai Image 4B! That's right, 1-bit diffusion models are here. Only ~3GB in size (FLUX.2 Klein 4B is 16GB). The most shocking part? It can run 100% locally in your browser. Try it now! 👇

Xenova

184,731 views • 4 months ago

NEW: OpenAI releases Privacy Filter, their first open model of 2026! 🤗 Apache-2.0! It's a bidirectional token-classification adaptation of GPT-OSS, trained to mask personally identifiable information (PII) in text. At only 1.5B params, it can even run locally in your browser!
1:22
xenovacom's profile picture

NEW: OpenAI releases Privacy Filter, their first open model of 2026! 🤗 Apache-2.0! It's a bidirectional token-classification adaptation of GPT-OSS, trained to mask personally identifiable information (PII) in text. At only 1.5B params, it can even run locally in your browser!

Xenova

220,238 views • 5 months ago

Jev isn't multimodal... but do you know what is? CLIP. A zero-shot multimodal classifier released nearly *6* years ago. Search 25,000 images in <50ms (no image labeling required). It can even run locally in your browser on WebGPU, powered by Transformers.js! Try it yourself 👇
0:20
xenovacom's profile picture

Jev isn't multimodal... but do you know what is? CLIP. A zero-shot multimodal classifier released nearly *6* years ago. Search 25,000 images in <50ms (no image labeling required). It can even run locally in your browser on WebGPU, powered by Transformers.js! Try it yourself 👇

Xenova

33,592 views • 26 days ago

We just open-sourced the world's fastest WebGPU kernels for 200+ machine learning operations. Specialized for your hardware. They run entirely locally in your browser. Now available on Hugging Face 🤗 Tell your agent to use @huggingface/kernels in your next project.
0:48
xenovacom's profile picture

We just open-sourced the world's fastest WebGPU kernels for 200+ machine learning operations. Specialized for your hardware. They run entirely locally in your browser. Now available on Hugging Face 🤗 Tell your agent to use @huggingface/kernels in your next project.

Xenova

21,552 views • 17 days ago

Chrome's new `window​.ai` feature is going to change the web forever! 🤯 It allows you to run Gemini Nano, a powerful 3.25B parameter LLM, 100% locally in your browser! We've also added experimental support to 🤗 Transformers.js, making it super easy to use! 😍 Check it out! 👇
0:34
xenovacom's profile picture

Chrome's new `window​.ai` feature is going to change the web forever! 🤯 It allows you to run Gemini Nano, a powerful 3.25B parameter LLM, 100% locally in your browser! We've also added experimental support to 🤗 Transformers.js, making it super easy to use! 😍 Check it out! 👇

Xenova

581,782 views • 2 years ago

A swarm of GPT 5.6 Sol agents spent over 40 hours optimizing a Kimi K3-like model from 65 to 406 tok/s. This animation follows their collaboration as they discover operator fusions, transform the execution graph, and develop new kernel algorithms.
2:50
xenovacom's profile picture

A swarm of GPT 5.6 Sol agents spent over 40 hours optimizing a Kimi K3-like model from 65 to 406 tok/s. This animation follows their collaboration as they discover operator fusions, transform the execution graph, and develop new kernel algorithms.

Xenova

75,771 views • 2 months ago

NEW: Mistral AI releases Mistral 3, a family of multimodal models, including three start-of-the-art dense models (3B, 8B, and 14B) and Mistral Large 3 (675B, 41B active). All Apache 2.0! 🤗 Surprisingly, the 3B is small enough to run 100% locally in your browser on WebGPU! 🤯
0:53
xenovacom's profile picture

NEW: Mistral AI releases Mistral 3, a family of multimodal models, including three start-of-the-art dense models (3B, 8B, and 14B) and Mistral Large 3 (675B, 41B active). All Apache 2.0! 🤗 Surprisingly, the 3B is small enough to run 100% locally in your browser on WebGPU! 🤯

Xenova

225,321 views • 10 months ago

The era of 1-bit LLMs is here — now with WebGPU acceleration! 🤯 It's incredible to think that a quantized 1.7B model (just 290MB in size) can run at ~100 tokens per second entirely in your browser. Try the demo yourself 👇
0:33
xenovacom's profile picture

The era of 1-bit LLMs is here — now with WebGPU acceleration! 🤯 It's incredible to think that a quantized 1.7B model (just 290MB in size) can run at ~100 tokens per second entirely in your browser. Try the demo yourself 👇

Xenova

105,543 views • 6 months ago

Okay, this is actually insane... You can now run LFM2.5-1.2B-Thinking (a 1.2B parameter LLM from @LiquidAI) at over 200 tokens per second directly in your browser on WebGPU! 🤯 Zero install. Fully private. Blazingly fast. Powered by Transformers.js and ONNX Runtime Web
0:45
xenovacom's profile picture

Okay, this is actually insane... You can now run LFM2.5-1.2B-Thinking (a 1.2B parameter LLM from @LiquidAI) at over 200 tokens per second directly in your browser on WebGPU! 🤯 Zero install. Fully private. Blazingly fast. Powered by Transformers.js and ONNX Runtime Web

Xenova

104,476 views • 7 months ago

NEW: Alibaba just released Qwen 3.5 Small — a family of powerful multimodal models available in a range of sizes (0.8B, 2B, 4B, and 9B parameters). Perfect for on-device applications! They can even run 100% locally in your browser on WebGPU, powered by Transformers.js! 🤯
0:46
xenovacom's profile picture

NEW: Alibaba just released Qwen 3.5 Small — a family of powerful multimodal models available in a range of sizes (0.8B, 2B, 4B, and 9B parameters). Perfect for on-device applications! They can even run 100% locally in your browser on WebGPU, powered by Transformers.js! 🤯

Xenova

102,592 views • 7 months ago

NEW: Ternary Bonsai 2 just landed on Hugging Face — a 27B reasoning model in ternary weights, built for the agentic era 🤯 9x smaller than FP16 while retaining 98.2% of the intelligence. At <6GB in size, it can even run 100% locally in your browser on WebGPU! Try it yourself 👇
1:03
xenovacom's profile picture

NEW: Ternary Bonsai 2 just landed on Hugging Face — a 27B reasoning model in ternary weights, built for the agentic era 🤯 9x smaller than FP16 while retaining 98.2% of the intelligence. At <6GB in size, it can even run 100% locally in your browser on WebGPU! Try it yourself 👇

Xenova

18,245 views • 1 month 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
xenovacom's profile picture

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

94,623 views • 7 months ago

It's finally possible: real-time in-browser speech recognition with OpenAI Whisper! 🤯 The model runs fully on-device using Transformers.js and ONNX Runtime Web, and supports multilingual transcription across 100 different languages! 🔥 Check out the demo (+ source code)! 👇
0:25
xenovacom's profile picture

It's finally possible: real-time in-browser speech recognition with OpenAI Whisper! 🤯 The model runs fully on-device using Transformers.js and ONNX Runtime Web, and supports multilingual transcription across 100 different languages! 🔥 Check out the demo (+ source code)! 👇

Xenova

262,819 views • 2 years ago