Loading video...

Video Failed to Load

Go Home

This doesn't feel like it should be possible. Muse Glimmer 30B can now run locally in your browser on WebGPU... at the same speed as llama.cpp (~25 tok/s on my M4 Max)! Just open a website. No installation required.

xenovacom's profile picture

Xenova

20,595 subscribers

21,280 views • 19 days ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

BOOM! 💥 Today I added WebGPU support for Andrej Karpathy's nanochat models, meaning they can run 100% locally in your browser (no server)! The d32 version runs at over 50 tps on my M4 Max 🚀 Pretty wild that you can now deploy AI applications using just a single index.html file 😅
0:20

BOOM! 💥 Today I added WebGPU support for Andrej Karpathy's nanochat models, meaning they can run 100% locally in your browser (no server)! The d32 version runs at over 50 tps on my M4 Max 🚀 Pretty wild that you can now deploy AI applications using just a single index.html file 😅

Xenova

95,481 views • 10 months ago

Meta opened the weights this morning. It's already living on a Mac. Muse Glimmer 30B, running locally in Osaurus. It analyzed an image and built a playable game. Your hardware. Your model. No subscription.
0:40

Meta opened the weights this morning. It's already living on a Mac. Muse Glimmer 30B, running locally in Osaurus. It analyzed an image and built a playable game. Your hardware. Your model. No subscription.

Osaurus

23,349 views • 20 days 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

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

173,953 views • 13 days 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

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 • 6 months ago

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 views • 5 months ago

AI at Meta's Muse Glimmer (30B dense, open-weights) launches with SGLang day-0 support. We got ~230 tok/s on a single RTX 5090, with NVFP4 + DFlash on. It also works out of the box on NVIDIA AI Developer RTX Pro 6000, DGX Spark, and MLX for Mac. Speed and reliability have always been the blockers for a local agent. SGLang and Muse Glimmer make a local agent that's blazing fast, always on, and gets things done. Go build and run a local agent on your own machine!🚀
0:32

AI at Meta's Muse Glimmer (30B dense, open-weights) launches with SGLang day-0 support. We got ~230 tok/s on a single RTX 5090, with NVFP4 + DFlash on. It also works out of the box on NVIDIA AI Developer RTX Pro 6000, DGX Spark, and MLX for Mac. Speed and reliability have always been the blockers for a local agent. SGLang and Muse Glimmer make a local agent that's blazing fast, always on, and gets things done. Go build and run a local agent on your own machine!🚀

LMSYS Org

43,106 views • 20 days ago

Introducing Supertonic WebGPU: blazingly fast text-to-speech running 100% locally in your browser. ⚡️ Generate free audiobooks in seconds, no installation required. In this example, I created a 5-hour audiobook of The Great Gatsby in less than 3 minutes! 🤯 Try it yourself! 👇
1:28

Introducing Supertonic WebGPU: blazingly fast text-to-speech running 100% locally in your browser. ⚡️ Generate free audiobooks in seconds, no installation required. In this example, I created a 5-hour audiobook of The Great Gatsby in less than 3 minutes! 🤯 Try it yourself! 👇

Xenova

23,497 views • 9 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

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

484,504 views • 2 months ago

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 views • 1 year 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

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 • 5 months ago

IBM just released Granite 4.0, their latest series of small language models! These models excel at agentic workflows (tool calling), document analysis, RAG, and more. 🚀 The "Micro" (3.4B) model can even run 100% locally in your browser on WebGPU, powered by 🤗 Transformers.js!
0:34

IBM just released Granite 4.0, their latest series of small language models! These models excel at agentic workflows (tool calling), document analysis, RAG, and more. 🚀 The "Micro" (3.4B) model can even run 100% locally in your browser on WebGPU, powered by 🤗 Transformers.js!

Xenova

82,893 views • 11 months 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 • 5 months ago

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 views • 1 year ago

New Muse Glimmer 30B destroyed Gemma 4 31B at making retro arcade games! We gave three models the same task and compared one-shot outputs. Muse Glimmer 30B, Gemma 4 31B and Qwen3.6 27B each ran locally on its own RTX 5090 with 32GB VRAM Tasks: - Space Invaders - Tetris - Arkanoid with multiball Outputs: Muse Glimmer 30B: 83.4K tokens, 17.7 min Qwen3.6 27B: 23.7K tokens, 5.4 min Gemma 4 31B: 17.8K tokens, 4.5 min Glimmer's games play like the originals. The alien fleet speeds up with every kill, the blocks lock and lines clear, the bricks break. Nothing froze or crashed. Gemma broke on Tetris, its bot piles every piece against the left wall until the stack hits the ceiling with half the well empty. Qwen finished all three but some of its Arkanoid balls phase straight through the paddle. Run Muse Glimmer yourself in Atomic Chat from day 0!
0:26

New Muse Glimmer 30B destroyed Gemma 4 31B at making retro arcade games! We gave three models the same task and compared one-shot outputs. Muse Glimmer 30B, Gemma 4 31B and Qwen3.6 27B each ran locally on its own RTX 5090 with 32GB VRAM Tasks: - Space Invaders - Tetris - Arkanoid with multiball Outputs: Muse Glimmer 30B: 83.4K tokens, 17.7 min Qwen3.6 27B: 23.7K tokens, 5.4 min Gemma 4 31B: 17.8K tokens, 4.5 min Glimmer's games play like the originals. The alien fleet speeds up with every kill, the blocks lock and lines clear, the bricks break. Nothing froze or crashed. Gemma broke on Tetris, its bot piles every piece against the left wall until the stack hits the ceiling with half the well empty. Qwen finished all three but some of its Arkanoid balls phase straight through the paddle. Run Muse Glimmer yourself in Atomic Chat from day 0!

atomic.chat

38,922 views • 20 days ago

128GB in Framework Desktop means you can run giant models locally like AI at Meta's Llama 4 Scout. This is a 109B MoE model with 17B active parameters. At Q6 this runs at >14 tok/s on LM Studio on Fedora 42!
1:05

128GB in Framework Desktop means you can run giant models locally like AI at Meta's Llama 4 Scout. This is a 109B MoE model with 17B active parameters. At Q6 this runs at >14 tok/s on LM Studio on Fedora 42!

Framework

30,053 views • 1 year ago

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 views • 1 year ago

I ran a 35-billion parameter AI agent on a $600 Mac mini. Specs: M4 Mac-Mini 16GB RAM The model doesn't fit in RAM. It pages from the SSD at 30 tokens/second. On NVIDIA, the same paging gives you 1.6 tok/s. Apple Silicon gives you 30. That's 18.6x faster. No cloud. No API keys. $0/month. Here's what it can do 🧵
1:39

I ran a 35-billion parameter AI agent on a $600 Mac mini. Specs: M4 Mac-Mini 16GB RAM The model doesn't fit in RAM. It pages from the SSD at 30 tokens/second. On NVIDIA, the same paging gives you 1.6 tok/s. Apple Silicon gives you 30. That's 18.6x faster. No cloud. No API keys. $0/month. Here's what it can do 🧵

thestreamingdev()

730,447 views • 5 months ago