Загрузка видео...

Не удалось загрузить видео

На главную

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

xenovacom's profile picture

Xenova

16,101 subscribers

103,001 просмотров • 5 месяцев назад •via X (Twitter)

Новости и политикаНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Woah... This is the fastest Transformers.js has ever been! 🤯 Run a 1.7B LLM 100% locally in your browser at over 130 tokens per second! 🚀 No server required. ⚡️ WebGPU-accelerated in-browser inference 📦 Optimized ONNX exports w/ GQA 💬 Multi-round conversations w/ KV caching
0:20

Woah... This is the fastest Transformers.js has ever been! 🤯 Run a 1.7B LLM 100% locally in your browser at over 130 tokens per second! 🚀 No server required. ⚡️ WebGPU-accelerated in-browser inference 📦 Optimized ONNX exports w/ GQA 💬 Multi-round conversations w/ KV caching

Xenova

54,099 просмотров • 1 год назад

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

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 просмотров • 6 месяцев назад

WebGPU is INSANE! 🤯 Here's a 24B parameter model running locally in a web browser, at a blazing ~50 tokens/second on my M4 Max. ⚡️ It's the largest model we've ever run with Transformers.js... and we're not stopping here. Big announcement soon.
1:05

WebGPU is INSANE! 🤯 Here's a 24B parameter model running locally in a web browser, at a blazing ~50 tokens/second on my M4 Max. ⚡️ It's the largest model we've ever run with Transformers.js... and we're not stopping here. Big announcement soon.

Xenova

36,251 просмотров • 4 месяцев назад

Okay this is insane... WebGPU-accelerated semantic video tracking, powered by DINOv3 and Transformers.js! 🤯 This will revolutionize AI-powered video editors... which can now run 100% locally in your browser, no server inference required (costs $0)! 😍 Who's building this?
0:22

Okay this is insane... WebGPU-accelerated semantic video tracking, powered by DINOv3 and Transformers.js! 🤯 This will revolutionize AI-powered video editors... which can now run 100% locally in your browser, no server inference required (costs $0)! 😍 Who's building this?

Xenova

42,882 просмотров • 11 месяцев назад

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 просмотров • 4 месяцев назад

I seriously cannot believe this is a 0.6B LLM! 🤯 Qwen just released Qwen3, a series of hybrid reasoning models that allow you to control how much "thinking" the model does for a given task. They can even run locally in your browser on WebGPU with 🤗 Transformers.js!
0:24

I seriously cannot believe this is a 0.6B LLM! 🤯 Qwen just released Qwen3, a series of hybrid reasoning models that allow you to control how much "thinking" the model does for a given task. They can even run locally in your browser on WebGPU with 🤗 Transformers.js!

Xenova

74,954 просмотров • 1 год назад

NEW: Real-time conversational AI models can now run 100% locally in your browser! 🤯 🔐 Privacy by design (no data leaves your device) 💰 Completely free... forever 📦 Zero installation required, just visit a website ⚡️ Blazingly-fast WebGPU-accelerated inference Try it out! 👇
0:58

NEW: Real-time conversational AI models can now run 100% locally in your browser! 🤯 🔐 Privacy by design (no data leaves your device) 💰 Completely free... forever 📦 Zero installation required, just visit a website ⚡️ Blazingly-fast WebGPU-accelerated inference Try it out! 👇

Xenova

12,094 просмотров • 1 год назад

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

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

105,446 просмотров • 4 месяцев назад

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

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 просмотров • 5 месяцев назад

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 просмотров • 5 месяцев назад

OmniParser, the new screen parsing tool from Microsoft (and #1 trending model on Hugging Face), can now run 100% locally in your browser with Transformers.js! 🤯 Who's going to be the first to turn this into a browser extension? 👀 Endless possibilities! Demo & code below! 👇
1:17

OmniParser, the new screen parsing tool from Microsoft (and #1 trending model on Hugging Face), can now run 100% locally in your browser with Transformers.js! 🤯 Who's going to be the first to turn this into a browser extension? 👀 Endless possibilities! Demo & code below! 👇

Xenova

64,560 просмотров • 1 год назад

Not enough people are talking about NVIDIA's new Nemotron-3-Nano (4B) model! 🤯 Hybrid Mamba + Attention architecture, designed as a unified model for reasoning and non-reasoning tasks. So small and efficient, it can run 100% locally in your web browser at 75 tokens per second.
1:06

Not enough people are talking about NVIDIA's new Nemotron-3-Nano (4B) model! 🤯 Hybrid Mamba + Attention architecture, designed as a unified model for reasoning and non-reasoning tasks. So small and efficient, it can run 100% locally in your web browser at 75 tokens per second.

Xenova

50,063 просмотров • 4 месяцев назад

Last week I spent $20,000 on Mac Studios so I could run OpenClaw locally Fully powered by local AI models running 24/7 Now my agent: • Is doing tasks 24/7/365 • Doesn't cost any tokens • Is fully private In this video I cover how it works and how you can do the same thing:
19:14

Last week I spent $20,000 on Mac Studios so I could run OpenClaw locally Fully powered by local AI models running 24/7 Now my agent: • Is doing tasks 24/7/365 • Doesn't cost any tokens • Is fully private In this video I cover how it works and how you can do the same thing:

Alex Finn

573,575 просмотров • 6 месяцев назад

RealBriefly has officially released! Decentralized media is now live on the XRP Ledger! A new era in digital media on the XRP Ledger focused on global content, covering markets, events, news, and real-time information from around the world. Write, publish, get paid (in $REAL tokens). You can now earn directly on the XRP Ledger through decentralized media. Publish articles and discussions and receive payments in REAL tokens per post. This movement is powered by the RealFi payment solution and the Real Token. Sign up at and start getting paid today!
0:33

RealBriefly has officially released! Decentralized media is now live on the XRP Ledger! A new era in digital media on the XRP Ledger focused on global content, covering markets, events, news, and real-time information from around the world. Write, publish, get paid (in $REAL tokens). You can now earn directly on the XRP Ledger through decentralized media. Publish articles and discussions and receive payments in REAL tokens per post. This movement is powered by the RealFi payment solution and the Real Token. Sign up at and start getting paid today!

Real Briefly

97,894 просмотров • 3 месяцев назад

turned this into a web app you can use with your own obsidian vault! no install, just one html file: point it at your notes folder, it embeds everything with gemini, clusters by meaning, and renders the 3d network in your browser. available now for x/twitter subscribers &lt;3
0:30

turned this into a web app you can use with your own obsidian vault! no install, just one html file: point it at your notes folder, it embeds everything with gemini, clusters by meaning, and renders the 3d network in your browser. available now for x/twitter subscribers &lt;3

Kat ⊷ the Poet Engineer

105,960 просмотров • 5 месяцев назад

You can now use OpenAIReview directly in your browser 📷. This is a part of our mission to make quality AI-assisted reviewing open and accessible to everyone. Reviews on the web version are free of charge, and you can get up to 3 reviews a day. Try it here!
0:52

You can now use OpenAIReview directly in your browser 📷. This is a part of our mission to make quality AI-assisted reviewing open and accessible to everyone. Reviews on the web version are free of charge, and you can get up to 3 reviews a day. Try it here!

Chenhao Tan

46,095 просмотров • 4 месяцев назад

🚀 ZKX Wallet Web App is NOW LIVE! The ZKX Wallet | The Secure and Private Wallet 🗽 is no longer tied to specific operating systems or app stores. We’ve rebuilt the same codebase that powers our ZKX Extension into a fully functional web app. With this release, ZKX Wallet is now accessible on any device with a modern web browser: • iOS (Safari, Chrome, etc.) • macOS • Windows • Linux • Android • ChromeOS • …and basically anything else with a browser No native installation is required for core access. You can also install it as a Progressive Web App (PWA) for a more app-like experience on supported devices. Your keys remain fully in your control. Even your HOT wallet is protected with encrypted passkey-based security, with no backup dependency or identity linking. Railgun shielding works seamlessly, hardware wallet support (including QR-based signing) is included, and you get unified private and public balance management across EVM chains and PulseChain. We can now ship new features almost daily to improve the wallet experience for our users. Privacy. Security. Accessibility. Universal.
0:48

🚀 ZKX Wallet Web App is NOW LIVE! The ZKX Wallet | The Secure and Private Wallet 🗽 is no longer tied to specific operating systems or app stores. We’ve rebuilt the same codebase that powers our ZKX Extension into a fully functional web app. With this release, ZKX Wallet is now accessible on any device with a modern web browser: • iOS (Safari, Chrome, etc.) • macOS • Windows • Linux • Android • ChromeOS • …and basically anything else with a browser No native installation is required for core access. You can also install it as a Progressive Web App (PWA) for a more app-like experience on supported devices. Your keys remain fully in your control. Even your HOT wallet is protected with encrypted passkey-based security, with no backup dependency or identity linking. Railgun shielding works seamlessly, hardware wallet support (including QR-based signing) is included, and you get unified private and public balance management across EVM chains and PulseChain. We can now ship new features almost daily to improve the wallet experience for our users. Privacy. Security. Accessibility. Universal.

Liberty Swap | C.R.O.P.S. on PulseChain 🗽

34,658 просмотров • 1 месяц назад

Obsidian CEO actually released the skill that lets your AI agent run your entire vault for you. It's called obsidian-skills. Install it into Claude Code, Codex, or OpenCode, and your agent can read, create, search, and organize notes directly, plus handle Markdown, Bases, and Canvas files without you touching a thing. This is the missing piece for an AI second brain. Your notes live in Obsidian, and now the agent actually knows how to work them. Want the full picture? We broke down how to build a complete AI second brain from scratch in the article below.
0:23

Obsidian CEO actually released the skill that lets your AI agent run your entire vault for you. It's called obsidian-skills. Install it into Claude Code, Codex, or OpenCode, and your agent can read, create, search, and organize notes directly, plus handle Markdown, Bases, and Canvas files without you touching a thing. This is the missing piece for an AI second brain. Your notes live in Obsidian, and now the agent actually knows how to work them. Want the full picture? We broke down how to build a complete AI second brain from scratch in the article below.

Simplifying AI

68,025 просмотров • 7 дней назад

Introducing NexaSDK for Android (Beta) — run the latest AI models locally, 9× more energy-efficient and 2× faster, on Android devices, powered by the Qualcomm Hexagon NPU. This is the first SDK to support NPU, GPU and CPU, unlocking the full power of every Android device — for example, LFM2-1.2B achieves 85 t/s on NPU vs 37 t/s on CPU. With just 3 lines of code, you can run the latest state-of-the-art models across every task, for example: Multimodal (Vision, Audio, Text): OmniNeural-4B Embedding: EmbeddingGemma from Google ASR: Parakeet-v3 from NVIDIA OCR: PaddleOCR from Baidu Inc. Rerank: Jina-reranker from Jina AI LLM: LFM2-1.2B from And we continue to deliver Day-0 model support across our framework. Build on-device AI into your Android app today and enjoy no cloud API cost, full privacy, and offline availability. Check out our Quickstart guide and example app below to get started in minutes.
0:54

Introducing NexaSDK for Android (Beta) — run the latest AI models locally, 9× more energy-efficient and 2× faster, on Android devices, powered by the Qualcomm Hexagon NPU. This is the first SDK to support NPU, GPU and CPU, unlocking the full power of every Android device — for example, LFM2-1.2B achieves 85 t/s on NPU vs 37 t/s on CPU. With just 3 lines of code, you can run the latest state-of-the-art models across every task, for example: Multimodal (Vision, Audio, Text): OmniNeural-4B Embedding: EmbeddingGemma from Google ASR: Parakeet-v3 from NVIDIA OCR: PaddleOCR from Baidu Inc. Rerank: Jina-reranker from Jina AI LLM: LFM2-1.2B from And we continue to deliver Day-0 model support across our framework. Build on-device AI into your Android app today and enjoy no cloud API cost, full privacy, and offline availability. Check out our Quickstart guide and example app below to get started in minutes.

NEXA AI

26,091 просмотров • 9 месяцев назад