Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Fuck yeah! Llama 3.2 3B running on your browser! 100% local, powered by WebGPU & MLC 🦙

reach_vb's profile picture

Vaibhav (VB) Srivastav

53,889 subscribers

282,043 Aufrufe • vor 1 Jahr •via X (Twitter)

GamingWissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von Vaibhav (VB) Srivastav
Vaibhav (VB) Srivastavvor 1 Jahr

Try it out here:

Profilbild von Varun
Varunvor 1 Jahr

sweet - i think even better on someone else’s browser :)

Profilbild von Petri Kuittinen
Petri Kuittinenvor 1 Jahr

Nice, but it seems to take forever to load, as I selected Llama-3.2-3B-instruct-q4f321-MLC. Only 20% 272 seconds. I have 500/500 Mbits/s fiber and normally it should take only 40 seconds to load the entire q4 model!

Profilbild von Vaibhav (VB) Srivastav
Vaibhav (VB) Srivastavvor 1 Jahr

Not sure! But could be a browser/ transient error in loading weights.

Profilbild von 🐧 lalo adrian morales 𝕏
🐧 lalo adrian morales 𝕏vor 1 Jahr

it's so good!!! l love being able to download such powerful things and run them without wifi and then make software that calls to these local llms... it's the new arcade game

Profilbild von Anthonix
Anthonixvor 1 Jahr

What about Safari? Sorta sucks to have to use Chrome.

Profilbild von Beat Sieber
Beat Siebervor 1 Jahr

Runs on my 4 year old Laptop with 16 GB of RAM in Chrome. Cool!

Profilbild von Mike D
Mike Dvor 1 Jahr

@_philschmid Light em up 🔥🔥🔥

Profilbild von George Siosi Samuels
George Siosi Samuelsvor 1 Jahr

@BrianRoemmele

Profilbild von liuyo
liuyovor 1 Jahr

It has finally come

Ähnliche Videos

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 Aufrufe • vor 1 Jahr

Introducing Moonshine Web: real-time speech recognition running 100% locally in your browser! 🚀 Faster and more accurate than Whisper 🔒 Privacy-focused (no data leaves your device) ⚡️ WebGPU accelerated (w/ WASM fallback) 🔥 Powered by ONNX Runtime Web and Transformers.js
0:40

Introducing Moonshine Web: real-time speech recognition running 100% locally in your browser! 🚀 Faster and more accurate than Whisper 🔒 Privacy-focused (no data leaves your device) ⚡️ WebGPU accelerated (w/ WASM fallback) 🔥 Powered by ONNX Runtime Web and Transformers.js

Xenova

27,940 Aufrufe • vor 1 Jahr

Run any LLM like Llama 3.2 directly from Hugging Face using Ollama on your local computer (100% free and without internet).
0:46

Run any LLM like Llama 3.2 directly from Hugging Face using Ollama on your local computer (100% free and without internet).

Shubham Saboo

33,551 Aufrufe • vor 1 Jahr

Announcing An open source wireframe to app tool powered by Llama 3.2 vision. Upload a screenshot of a simple site/design & get code. 100% free and open source.
0:28

Announcing An open source wireframe to app tool powered by Llama 3.2 vision. Upload a screenshot of a simple site/design & get code. 100% free and open source.

Hassan

186,057 Aufrufe • vor 1 Jahr

Yeah, bloom node in #threejs r167! Let's make some particles! Linked this time, inspired by Keijiro Takahashi , but in your browser, on your GPU :) Link to play below ⬇️ #tsl #webgpu #compute
0:36

Yeah, bloom node in #threejs r167! Let's make some particles! Linked this time, inspired by Keijiro Takahashi , but in your browser, on your GPU :) Link to play below ⬇️ #tsl #webgpu #compute

Christophe Choffel

45,796 Aufrufe • vor 2 Jahren

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 Aufrufe • vor 1 Jahr

Hermes agent running in private browser on free local models Private by design. Local. Open-source
0:25

Hermes agent running in private browser on free local models Private by design. Local. Open-source

Sigma Browser

60,768 Aufrufe • vor 3 Monaten

Whisper Large v3 Turbo running 100% local on Mac - powered by Apple Neural Engine! 🔥 Brought to you by argmax ⚡
0:44

Whisper Large v3 Turbo running 100% local on Mac - powered by Apple Neural Engine! 🔥 Brought to you by argmax ⚡

Vaibhav (VB) Srivastav

51,389 Aufrufe • vor 1 Jahr

Someone made Samantha from the HER movie 💑 Running entirely in your browser 🤯- powered by transformers.js
1:00

Someone made Samantha from the HER movie 💑 Running entirely in your browser 🤯- powered by transformers.js

Victor M

37,648 Aufrufe • vor 1 Jahr

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 Aufrufe • vor 1 Jahr

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

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

225,178 Aufrufe • vor 8 Monaten

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 Aufrufe • vor 5 Monaten

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 Aufrufe • vor 10 Monaten

Create OpenAI like AI assistant with Llama 3.2 deployed locally on your computer (100% free and without internet):
0:51

Create OpenAI like AI assistant with Llama 3.2 deployed locally on your computer (100% free and without internet):

Shubham Saboo

73,631 Aufrufe • vor 1 Jahr