Loading video...

Video Failed to Load

Go Home

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!

calebfahlgren's profile picture

Caleb

3,953 subscribers

41,579 views • 1 year ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

9 Comments

Caleb's profile picture
Caleb1 year ago

The 72B is getting tons of love, but @Alibaba_Qwen is really killing it in the 7B to edge range as well with the code models being really intriguing!

Binyuan Hui's profile picture
Binyuan Hui1 year ago

Wow this is really cool! Thank you! By the way we've also released a technical report.

Caleb's profile picture
Caleb1 year ago

Love it! Thanks for the amazing work and models!

Erik Kaunismäki's profile picture
Erik Kaunismäki1 year ago

nice 🔥 is next step hooking up @e2b_dev --> exec code in sandbox --> get back the html & render in the space? 👀

0xMe7o's profile picture
0xMe7o1 year ago

Just try it out! It did so well as such a small LLM👍

Stiven's profile picture
Stiven1 year ago

Running smoothly on MacBook Air M1 and even on my Iphone, but not as good as yours.

justboulatbek's profile picture
justboulatbek1 year ago

How did you install it on mac?

Valter Mazzola's profile picture
Valter Mazzola1 year ago

Mac model?

🇺🇦🇮🇱dmitriy samsonov's profile picture
🇺🇦🇮🇱dmitriy samsonov1 year ago

this can't be real

Related Videos

Running Qwen2.5-Coder (0.5B params) locally on a Mac Intel Core i5 with CodeGPT and Ollama 🤩 In seconds, it explains Python code... all private and secure! Download CodeGPT from the VSCode Marketplace! 👏 Qwen ollama CodeGPT
0:27

Running Qwen2.5-Coder (0.5B params) locally on a Mac Intel Core i5 with CodeGPT and Ollama 🤩 In seconds, it explains Python code... all private and secure! Download CodeGPT from the VSCode Marketplace! 👏 Qwen ollama CodeGPT

Daniel San

30,613 views • 1 year 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

🚀 Tensorplex Dojo (Subnet 52) in action! Meet DOJO-INTERFACE-CODER-7B: Qwen2.5-Coder-7B-Instruct, fine-tuned with Dojo datasets to craft stunning front-end UIs! ✨ Generates beautiful, interactive interfaces ✨ Trained on synthetic data with distributed human feedback ✨ Powered by (Subnet 52) on Bittensor 👇
0:31

🚀 Tensorplex Dojo (Subnet 52) in action! Meet DOJO-INTERFACE-CODER-7B: Qwen2.5-Coder-7B-Instruct, fine-tuned with Dojo datasets to craft stunning front-end UIs! ✨ Generates beautiful, interactive interfaces ✨ Trained on synthetic data with distributed human feedback ✨ Powered by (Subnet 52) on Bittensor 👇

Tensorplex Labs

18,281 views • 1 year ago

100% Local LLM Coding with Bolt + Ollama + Qwen Qwen just dropped their qwen2.5-coder-30B and it's on ollama. Finally a model good enough to use instead of gpt-4o or claude. Now with Qwen, Bolt perfectly displays the app preview with Ollama. Run it with 1 click.
1:00

100% Local LLM Coding with Bolt + Ollama + Qwen Qwen just dropped their qwen2.5-coder-30B and it's on ollama. Finally a model good enough to use instead of gpt-4o or claude. Now with Qwen, Bolt perfectly displays the app preview with Ollama. Run it with 1 click.

cocktail peanut

52,630 views • 1 year ago

M4 Mac AI Coding Cluster Uses EXO Labs to run LLMs (here Qwen 2.5 Coder 32B at 18 tok/sec) distributed across 4 M4 Mac Minis (Thunderbolt 5 80Gbps) and a MacBook Pro M4 Max. Local alternative to Cursor (benchmark comparison soon).
0:20

M4 Mac AI Coding Cluster Uses EXO Labs to run LLMs (here Qwen 2.5 Coder 32B at 18 tok/sec) distributed across 4 M4 Mac Minis (Thunderbolt 5 80Gbps) and a MacBook Pro M4 Max. Local alternative to Cursor (benchmark comparison soon).

Alex Cheema

517,686 views • 1 year ago

⚡Technical Showcase: Peer-to-peer GPU sharing, entirely in the browser. AI Grid lets you run LLMs locally with WebGPU and either donate your spare compute to the network or borrow from someone else's machine. No installs, no cloud. Decentralized inference with nothing but a URL. 🔗 #WebGPU #WebLLM #WebAI #DistributedCompute #ArtificialInteligence
1:00

⚡Technical Showcase: Peer-to-peer GPU sharing, entirely in the browser. AI Grid lets you run LLMs locally with WebGPU and either donate your spare compute to the network or borrow from someone else's machine. No installs, no cloud. Decentralized inference with nothing but a URL. 🔗 #WebGPU #WebLLM #WebAI #DistributedCompute #ArtificialInteligence

WebGL / WebGPU

17,157 views • 6 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

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 • 5 months ago

Qwen2.5-coder is a game changer for secure, private, and local code development in VSCode 🤩 We've been testing the latest Qwen models running locally in VSCode through ollama and CodeGPT, and the results are incredible I highly recommend downloading and trying out these models directly from #CodeGPT.. you'll be impressed!
0:24

Qwen2.5-coder is a game changer for secure, private, and local code development in VSCode 🤩 We've been testing the latest Qwen models running locally in VSCode through ollama and CodeGPT, and the results are incredible I highly recommend downloading and trying out these models directly from #CodeGPT.. you'll be impressed!

Daniel San

50,573 views • 1 year ago

SDF raytracing in a browser. WebGPU, SDF is 256x256x256, the build is done on the GPU using 2-level BVH (TLAS+BLAS).
0:59

SDF raytracing in a browser. WebGPU, SDF is 256x256x256, the build is done on the GPU using 2-level BVH (TLAS+BLAS).

Alex Goldring

31,256 views • 6 months ago

real-time vision in your browser 🔥 try out YOLO26 for pose estimation and detection built on WebGPU ⚡️
0:21

real-time vision in your browser 🔥 try out YOLO26 for pose estimation and detection built on WebGPU ⚡️

merve

46,395 views • 6 months 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

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 views • 5 months 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

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

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

Claude Code costs $200/month here's how to run it for free. 4 commands. 10 minutes step 1 - install Ollama runs AI models locally → download from → install. it runs in background on localhost:11434 step 2 - download a coding model → ollama pull qwen2.5-coder:14b (7b for 8GB RAM, 32b for 32GB+ RAM) step 3 - redirect Claude Code to your machine → export ANTHROPIC_BASE_URL= → export ANTHROPIC_MODEL=qwen2.5-coder:14b step 4 - launch → claude → "make a hello world website" → it reads files, writes code, runs commands. locally. free same agent loop. same tools. $0/month the $200 was for convenience the capability was always free like + bookmark - you'll need this
1:41

Claude Code costs $200/month here's how to run it for free. 4 commands. 10 minutes step 1 - install Ollama runs AI models locally → download from → install. it runs in background on localhost:11434 step 2 - download a coding model → ollama pull qwen2.5-coder:14b (7b for 8GB RAM, 32b for 32GB+ RAM) step 3 - redirect Claude Code to your machine → export ANTHROPIC_BASE_URL= → export ANTHROPIC_MODEL=qwen2.5-coder:14b step 4 - launch → claude → "make a hello world website" → it reads files, writes code, runs commands. locally. free same agent loop. same tools. $0/month the $200 was for convenience the capability was always free like + bookmark - you'll need this

self.dll

177,814 views • 4 months ago

Alibaba engineer who leads Qwen explained the future of open agent models in 25 minutes - better than $2000 LLM training courses. pre-train the base ->SFT -> RLHF -> tool use -> multi-modal -> ship a whole family (chat / VL / coder / math / QwQ). That loop is why Qwen quietly became the most downloaded open model family on Hugging Face. Qwen base + Qwen-VL + Qwen-Coder + QwQ reasoning - that's the stack. Watch and save it, then read the article below.
25:13

Alibaba engineer who leads Qwen explained the future of open agent models in 25 minutes - better than $2000 LLM training courses. pre-train the base ->SFT -> RLHF -> tool use -> multi-modal -> ship a whole family (chat / VL / coder / math / QwQ). That loop is why Qwen quietly became the most downloaded open model family on Hugging Face. Qwen base + Qwen-VL + Qwen-Coder + QwQ reasoning - that's the stack. Watch and save it, then read the article below.

h100envy

114,009 views • 1 month ago

🚀 Exciting News! We're thrilled to announce the launch of Qwen Chat ( ) – your new go-to Web UI for interacting with Qwen models! 🌟 💬 Chat effortlessly with our flagship model Qwen2.5-Plus , explore vision-language capabilities with Qwen2-VL-Max , and dive into reasoning models like QwQ and QVQ, code with coding expert Qwen2.5-Coder-32B-Instruct, etc. ✨ Key Features: * Choose & compare multiple models in one interface * Upload documents & get answers based on them * Preview mode with HTML support * Upload images for visual understanding 🌟 Coming Soon: Web search, image generation, voice mode, and more! 🔗 Ready to experience the future? Start to chat with Qwen today 💬 Feel free to send us your feedback and suggestions!
1:53

🚀 Exciting News! We're thrilled to announce the launch of Qwen Chat ( ) – your new go-to Web UI for interacting with Qwen models! 🌟 💬 Chat effortlessly with our flagship model Qwen2.5-Plus , explore vision-language capabilities with Qwen2-VL-Max , and dive into reasoning models like QwQ and QVQ, code with coding expert Qwen2.5-Coder-32B-Instruct, etc. ✨ Key Features: * Choose & compare multiple models in one interface * Upload documents & get answers based on them * Preview mode with HTML support * Upload images for visual understanding 🌟 Coming Soon: Web search, image generation, voice mode, and more! 🔗 Ready to experience the future? Start to chat with Qwen today 💬 Feel free to send us your feedback and suggestions!

Qwen

215,137 views • 1 year ago