Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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 görüntüleme • 1 yıl önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

9 Yorum

Caleb profil fotoğrafı
Caleb1 yıl önce

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 profil fotoğrafı
Binyuan Hui1 yıl önce

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

Caleb profil fotoğrafı
Caleb1 yıl önce

Love it! Thanks for the amazing work and models!

Erik Kaunismäki profil fotoğrafı
Erik Kaunismäki1 yıl önce

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

0xMe7o profil fotoğrafı
0xMe7o1 yıl önce

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

Stiven profil fotoğrafı
Stiven1 yıl önce

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

justboulatbek profil fotoğrafı
justboulatbek1 yıl önce

How did you install it on mac?

Valter Mazzola profil fotoğrafı
Valter Mazzola1 yıl önce

Mac model?

🇺🇦🇮🇱dmitriy samsonov profil fotoğrafı
🇺🇦🇮🇱dmitriy samsonov1 yıl önce

this can't be real

Benzer Videolar

Qwen 2.5 Coder is here. Want to build a website in seconds? For free? Read on.
1:10

Qwen 2.5 Coder is here. Want to build a website in seconds? For free? Read on.

Julian Goldie SEO

30,188 görüntüleme • 1 yıl önce

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 görüntüleme • 1 yıl önce

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 görüntüleme • 1 yıl önce

Fuck yeah! Llama 3.2 3B running on your browser! 100% local, powered by WebGPU & MLC 🦙
1:22

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

Vaibhav (VB) Srivastav

282,006 görüntüleme • 1 yıl önce

Numbers in! Target: 150 tok/s browser-native Qwen 3.5 inference Achieved: 180 tok/s — Qwen 3.5 INT4, WebGPU, browser-only. No cloud, APIs, servers, just Pure WebGPU + WGSL optimizations, HF SafeTensors, single browser tab. Open AI, for real.
0:57

Numbers in! Target: 150 tok/s browser-native Qwen 3.5 inference Achieved: 180 tok/s — Qwen 3.5 INT4, WebGPU, browser-only. No cloud, APIs, servers, just Pure WebGPU + WGSL optimizations, HF SafeTensors, single browser tab. Open AI, for real.

Eric

256,656 görüntüleme • 3 ay önce

llama.vscode (powered by Qwen Coder)
0:37

llama.vscode (powered by Qwen Coder)

Georgi Gerganov

77,488 görüntüleme • 1 yıl önce

🚀 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 görüntüleme • 1 yıl önce

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

517,325 görüntüleme • 1 yıl önce

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 görüntüleme • 1 yıl önce

⚡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 görüntüleme • 4 ay önce

Qwen-Coder-Qoder is live! We’ve launched a customized model built on Alibaba’s Qwen-Coder, fine-tuned via large-scale RL specifically for the Qoder.
1:17

Qwen-Coder-Qoder is live! We’ve launched a customized model built on Alibaba’s Qwen-Coder, fine-tuned via large-scale RL specifically for the Qoder.

Qoder

178,024 görüntüleme • 4 ay önce

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 görüntüleme • 4 ay önce

Qwen 2.5 Coder Q4 M4 Max Inference test. Apple MLX vs Ollama: - MLX: 23.97 toks/sec 🥇🔥 - Ollama: 18.33 toks/sec 🥈 Here a video to show results
1:00

Qwen 2.5 Coder Q4 M4 Max Inference test. Apple MLX vs Ollama: - MLX: 23.97 toks/sec 🥇🔥 - Ollama: 18.33 toks/sec 🥈 Here a video to show results

Ivan Fioravanti ᯅ

34,881 görüntüleme • 1 yıl önce

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 görüntüleme • 1 yıl önce

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 görüntüleme • 5 ay önce

We've been partnering with Unity for Games to bring WebGPU to their engine, so their developers have everything they need to build immersive games in the browser. Learn more about WebGPU in Unity → Get started with WebGPU →
0:57

We've been partnering with Unity for Games to bring WebGPU to their engine, so their developers have everything they need to build immersive games in the browser. Learn more about WebGPU in Unity → Get started with WebGPU →

Chrome for Developers

18,190 görüntüleme • 2 yıl önce

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 görüntüleme • 5 ay önce