Have you tried webllm.mlc.ai?
You can basically use any <10B LLM directly in the browser using #WebLLM. .
You can basically use any <10B LLM directly in the browser using #WebLLM. .
WebLLM | Home
WebLLM: High-Performance In-Browser LLM Inference Engine
webllm.mlc.ai
November 24, 2024 at 6:36 PM
Have you tried webllm.mlc.ai?
You can basically use any <10B LLM directly in the browser using #WebLLM. .
You can basically use any <10B LLM directly in the browser using #WebLLM. .
🏖️🐻 Les Logiciels Libres de l'été, jour 78 :
WebLLM : un moteur Open Source permettant d’exécuter des LLM entièrement dans le navigateur, sans serveur d’inférence, grâce à l’accélération GPU fournie par WebGPU.
WebLLM : un moteur Open Source permettant d’exécuter des LLM entièrement dans le navigateur, sans serveur d’inférence, grâce à l’accélération GPU fournie par WebGPU.
September 8, 2026 at 5:31 PM
🏖️🐻 Les Logiciels Libres de l'été, jour 78 :
WebLLM : un moteur Open Source permettant d’exécuter des LLM entièrement dans le navigateur, sans serveur d’inférence, grâce à l’accélération GPU fournie par WebGPU.
WebLLM : un moteur Open Source permettant d’exécuter des LLM entièrement dans le navigateur, sans serveur d’inférence, grâce à l’accélération GPU fournie par WebGPU.
WebLLM : moteur d'inférence pour LLM directement dans le navigateur, accéléré par WebGPU. Zéro serveur, compatible API OpenAI (streaming, JSON-mode). Tourne avec Llama 3, Phi 3, Gemma, Mistral, Qwen2. Open source. ⬇️
https://github.com/mlc-ai/web-llm
📬 Recevoir ma veille
https://github.com/mlc-ai/web-llm
📬 Recevoir ma veille
September 23, 2026 at 10:00 AM
WebLLM : moteur d'inférence pour LLM directement dans le navigateur, accéléré par WebGPU. Zéro serveur, compatible API OpenAI (streaming, JSON-mode). Tourne avec Llama 3, Phi 3, Gemma, Mistral, Qwen2. Open source. ⬇️
https://github.com/mlc-ai/web-llm
📬 Recevoir ma veille
https://github.com/mlc-ai/web-llm
📬 Recevoir ma veille
This is insane! Structured generation in the browser with the new @hf.co SmolLM2-1.7B model
• Tiny 1.7B LLM running at 88 tokens / second ⚡
• Powered by MLC/WebLLM on WebGPU 🔥
• JSON Structured Generation entirely in the browser 🤏
• Tiny 1.7B LLM running at 88 tokens / second ⚡
• Powered by MLC/WebLLM on WebGPU 🔥
• JSON Structured Generation entirely in the browser 🤏
November 29, 2024 at 11:18 AM
This is insane! Structured generation in the browser with the new @hf.co SmolLM2-1.7B model
• Tiny 1.7B LLM running at 88 tokens / second ⚡
• Powered by MLC/WebLLM on WebGPU 🔥
• JSON Structured Generation entirely in the browser 🤏
• Tiny 1.7B LLM running at 88 tokens / second ⚡
• Powered by MLC/WebLLM on WebGPU 🔥
• JSON Structured Generation entirely in the browser 🤏
What if AI agents ran entirely in your browser?
Baris Guler takes that idea seriously in our first-ever guest post on the Mozilla.ai blog:
🧱 WebLLM + WASM + WebWorkers
💻 Rust, Go, Python, JS
🔒 Fully local. No API calls.
Read the post here:
blog.mozilla.ai/3w-for-in-br...
Baris Guler takes that idea seriously in our first-ever guest post on the Mozilla.ai blog:
🧱 WebLLM + WASM + WebWorkers
💻 Rust, Go, Python, JS
🔒 Fully local. No API calls.
Read the post here:
blog.mozilla.ai/3w-for-in-br...
3W for In-Browser AI: WebLLM + WASM + WebWorkers
🤝This is the first "guest post" in Mozilla.ai's blog (congratulations Baris!). His experiment, built upon the ideas of Mozilla.ai’s WASM agents blueprint, extends the concept of in-browser agents with...
blog.mozilla.ai
August 29, 2025 at 3:35 AM
What if AI agents ran entirely in your browser?
Baris Guler takes that idea seriously in our first-ever guest post on the Mozilla.ai blog:
🧱 WebLLM + WASM + WebWorkers
💻 Rust, Go, Python, JS
🔒 Fully local. No API calls.
Read the post here:
blog.mozilla.ai/3w-for-in-br...
Baris Guler takes that idea seriously in our first-ever guest post on the Mozilla.ai blog:
🧱 WebLLM + WASM + WebWorkers
💻 Rust, Go, Python, JS
🔒 Fully local. No API calls.
Read the post here:
blog.mozilla.ai/3w-for-in-br...
Free AI Chat, locally in your browser. 💻
- No signup required
- 100% data privacy
- No API keys 🔒
Supported Models:
• #SmolLM2
• #Qwen
• #Llama
• #DeepSeek R1
• #Phi
• #TinyLlama
• & More
🔗 zalt.me/tools/free-a...
#FreeAI #Free #WebGPU #AI #WebLLM #ChatGPT #JS #OpenSource #LLM #Chrome
- No signup required
- 100% data privacy
- No API keys 🔒
Supported Models:
• #SmolLM2
• #Qwen
• #Llama
• #DeepSeek R1
• #Phi
• #TinyLlama
• & More
🔗 zalt.me/tools/free-a...
#FreeAI #Free #WebGPU #AI #WebLLM #ChatGPT #JS #OpenSource #LLM #Chrome
June 30, 2026 at 2:59 AM
Started an Awesome Cross-Origin Storage list: github.com/tomayac/awes... . Transformers.js, WebLLM, wllama, Flutter, Emscripten, Nuxt and Vite plugins, and a bunch of demos… #Awesome #CrossOriginStorage
GitHub - tomayac/awesome-cross-origin-storage: A curated list of resources for the Cross-Origin Storage (COS) API
A curated list of resources for the Cross-Origin Storage (COS) API - tomayac/awesome-cross-origin-storage
github.com
July 4, 2026 at 7:00 PM
Started an Awesome Cross-Origin Storage list: github.com/tomayac/awes... . Transformers.js, WebLLM, wllama, Flutter, Emscripten, Nuxt and Vite plugins, and a bunch of demos… #Awesome #CrossOriginStorage
In-browser LLM inference gets serious 🧠
WebLLM runs LLMs directly in your browser with WebGPU acceleration, offering OpenAI API compatibility and enabling local, private AI tasks.
WebLLM runs LLMs directly in your browser with WebGPU acceleration, offering OpenAI API compatibility and enabling local, private AI tasks.
September 3, 2026 at 8:52 PM
In-browser LLM inference gets serious 🧠
WebLLM runs LLMs directly in your browser with WebGPU acceleration, offering OpenAI API compatibility and enabling local, private AI tasks.
WebLLM runs LLMs directly in your browser with WebGPU acceleration, offering OpenAI API compatibility and enabling local, private AI tasks.
Check out my three-part article series about the benefits of on-device large language models and learn how to add AI capabilities to your web apps: web.dev/articles/ai-... #GenAI #WebLLM #PromptAPI
Benefits and limits of large language models | Articles | web.dev
web.dev
January 13, 2025 at 4:38 PM
Check out my three-part article series about the benefits of on-device large language models and learn how to add AI capabilities to your web apps: web.dev/articles/ai-... #GenAI #WebLLM #PromptAPI
No, I am using webllm.mlc.ai. There you can play around with top-p and temperature. Same with the gemini API.
WebLLM | Home
WebLLM: High-Performance In-Browser LLM Inference Engine
webllm.mlc.ai
January 29, 2025 at 5:27 PM
No, I am using webllm.mlc.ai. There you can play around with top-p and temperature. Same with the gemini API.
What if we could use AI models like Llama 3.2 or Mistral 7B in the browser with JupyterLite? 🤯
Still at a very early stage of course, but making some good progress!
Thanks to WebLLM, which brings hardware accelerated language model inference onto web browsers, via WebGPU 🚀
Still at a very early stage of course, but making some good progress!
Thanks to WebLLM, which brings hardware accelerated language model inference onto web browsers, via WebGPU 🚀
February 17, 2025 at 8:00 AM
What if we could use AI models like Llama 3.2 or Mistral 7B in the browser with JupyterLite? 🤯
Still at a very early stage of course, but making some good progress!
Thanks to WebLLM, which brings hardware accelerated language model inference onto web browsers, via WebGPU 🚀
Still at a very early stage of course, but making some good progress!
Thanks to WebLLM, which brings hardware accelerated language model inference onto web browsers, via WebGPU 🚀
I've made a local AI chatbot that runs entirely in your browser on your device
It's a chatbot pretending to be a human pretending to be an artist pretending to be a crayfish. No data gets sent anywhere - everything happens locally using Phi-3.5-mini in your browser using WebLLM technology.
It's a chatbot pretending to be a human pretending to be an artist pretending to be a crayfish. No data gets sent anywhere - everything happens locally using Phi-3.5-mini in your browser using WebLLM technology.
Projects | Kristoffer Ørum
portiofiol of artist Kristoffer Ørum
oerum.org
August 26, 2025 at 5:33 PM
I've made a local AI chatbot that runs entirely in your browser on your device
It's a chatbot pretending to be a human pretending to be an artist pretending to be a crayfish. No data gets sent anywhere - everything happens locally using Phi-3.5-mini in your browser using WebLLM technology.
It's a chatbot pretending to be a human pretending to be an artist pretending to be a crayfish. No data gets sent anywhere - everything happens locally using Phi-3.5-mini in your browser using WebLLM technology.
🚀 Excited about the potential of Generative AI in the browser? I recently experimented with 𝗪𝗲𝗯𝗟𝗟𝗠, a library that lets you run #AI models right in your browser using WebGPU. It's impressive and hasn't crashed yet, even on my old MacBook Pro! 💻
#aiTech #buildInPublic #webDev - 1/3
#aiTech #buildInPublic #webDev - 1/3
January 14, 2025 at 12:19 PM
🚀 Excited about the potential of Generative AI in the browser? I recently experimented with 𝗪𝗲𝗯𝗟𝗟𝗠, a library that lets you run #AI models right in your browser using WebGPU. It's impressive and hasn't crashed yet, even on my old MacBook Pro! 💻
#aiTech #buildInPublic #webDev - 1/3
#aiTech #buildInPublic #webDev - 1/3
WebLLMを使ってクラウドもAPIキーも不要なAIブラウザ自動化ツール「On-device AI browser」
https://gigazine.net/news/20260214-on-device-browser-agent/
https://gigazine.net/news/20260214-on-device-browser-agent/
WebLLMを使ってクラウドもAPIキーも不要なAIブラウザ自動化ツール「On-device AI browser」
AI技術を応用して人の手で行っていた作業を自動化する流れはますます加速しており、特にウェブブラウザ上での操作を自動化するツールは多くのユーザーにとって有用そうです。しかしAI自動化ツールの多くはクラウドベースであるためAPIキーの取得といった煩雑な手順が必要だったりプライバシーに関する懸念が存在したりします。「On-device AI browser」はローカルにLLMをロードするためクラウドもAPIキーも不要なAIブラウザ自動化ツールです。
gigazine.net
February 14, 2026 at 6:00 AM
WebLLMを使ってクラウドもAPIキーも不要なAIブラウザ自動化ツール「On-device AI browser」
https://gigazine.net/news/20260214-on-device-browser-agent/
https://gigazine.net/news/20260214-on-device-browser-agent/
Front-end Digest №88: WebLLM, особливості Tailwind v4 та майбутнє Next.js
Front-end Digest №88: WebLLM, особливості Tailwind v4 та майбутнє Next.js
Олександр із Zfort Group підготував свіжий дайджест фронтенд-новин. Читайте про підтримку CSS у ESLint, можливості Deno 2.2, секрети підвищення INP у Next.js, а також про оптимізацію Vue.js із shallowRef. І не забудьте переглянути меми!
dlvr.it
February 24, 2025 at 1:04 PM
Front-end Digest №88: WebLLM, особливості Tailwind v4 та майбутнє Next.js
Just watched the @developers.google.com keynote.
Shouts to @una.im (fire blazer, btw) & @matthiasrohmer.bsky.social !
Just updated my Antigravity & added Modern Web Guidance.
Going to try that "Ask Gemini" with a #WebMCP demo I made. Currently it uses Prompt API and WebLLM.
Shouts to @una.im (fire blazer, btw) & @matthiasrohmer.bsky.social !
Just updated my Antigravity & added Modern Web Guidance.
Going to try that "Ask Gemini" with a #WebMCP demo I made. Currently it uses Prompt API and WebLLM.
May 19, 2026 at 10:18 PM
Just watched the @developers.google.com keynote.
Shouts to @una.im (fire blazer, btw) & @matthiasrohmer.bsky.social !
Just updated my Antigravity & added Modern Web Guidance.
Going to try that "Ask Gemini" with a #WebMCP demo I made. Currently it uses Prompt API and WebLLM.
Shouts to @una.im (fire blazer, btw) & @matthiasrohmer.bsky.social !
Just updated my Antigravity & added Modern Web Guidance.
Going to try that "Ask Gemini" with a #WebMCP demo I made. Currently it uses Prompt API and WebLLM.
I recently learned from one of @thdxr's tweets that people don't consider me a "build in public" person. So, I guess I need to change that.
Today, I'm dealing with WebLLM and how to use it to do "AI" stuff in my app without blowing my bootstrapped budget for the app I'm building, Messijo.
Today, I'm dealing with WebLLM and how to use it to do "AI" stuff in my app without blowing my bootstrapped budget for the app I'm building, Messijo.
December 14, 2025 at 1:18 AM
I recently learned from one of @thdxr's tweets that people don't consider me a "build in public" person. So, I guess I need to change that.
Today, I'm dealing with WebLLM and how to use it to do "AI" stuff in my app without blowing my bootstrapped budget for the app I'm building, Messijo.
Today, I'm dealing with WebLLM and how to use it to do "AI" stuff in my app without blowing my bootstrapped budget for the app I'm building, Messijo.
If the question is whether you can run LLMs in WebAssembly, the answer is yes already, today :)
chat.webllm.ai
But 3% of browsers still don't support WebAssembly, 18% don't WebGPU.
chat.webllm.ai
But 3% of browsers still don't support WebAssembly, 18% don't WebGPU.
WebLLM Chat
Chat with AI large language models running natively in your browser
chat.webllm.ai
April 2, 2026 at 7:53 PM
If the question is whether you can run LLMs in WebAssembly, the answer is yes already, today :)
chat.webllm.ai
But 3% of browsers still don't support WebAssembly, 18% don't WebGPU.
chat.webllm.ai
But 3% of browsers still don't support WebAssembly, 18% don't WebGPU.
WebLLM: high-performance in-browser LLM inference engine
An open-source project runs full LLMs entirely inside your browser tab, no server or API call needed.
An open-source project runs full LLMs entirely inside your browser tab, no server or API call needed.
WebLLM: high-performance in-browser LLM inference engine
An open-source project runs full LLMs entirely inside your browser tab, no server or API call needed.
github.com
September 3, 2026 at 10:15 AM
WebLLM: high-performance in-browser LLM inference engine
An open-source project runs full LLMs entirely inside your browser tab, no server or API call needed.
An open-source project runs full LLMs entirely inside your browser tab, no server or API call needed.
Local AI Chat: Browser-Native Language Models with Privacy Focus 🔒
#WebLLM Chat brings #AI conversations to your browser using #WebGPU - runs locally for complete #privacy and #offline use. Built on #opensource tech, supports #customLLM and image analysis. More at chat.webllm.ai
#WebLLM Chat brings #AI conversations to your browser using #WebGPU - runs locally for complete #privacy and #offline use. Built on #opensource tech, supports #customLLM and image analysis. More at chat.webllm.ai
November 21, 2024 at 6:44 PM
Local AI Chat: Browser-Native Language Models with Privacy Focus 🔒
#WebLLM Chat brings #AI conversations to your browser using #WebGPU - runs locally for complete #privacy and #offline use. Built on #opensource tech, supports #customLLM and image analysis. More at chat.webllm.ai
#WebLLM Chat brings #AI conversations to your browser using #WebGPU - runs locally for complete #privacy and #offline use. Built on #opensource tech, supports #customLLM and image analysis. More at chat.webllm.ai
Shared some Jupyter Frontends demos last week at Jupyter Open Studio Day (hosted by Bloomberg)!
Covered:
✨ JupyterLab 4.4, Notebook 7.4
🧪 JupyterLite 0.6
🌐 In-browser Python/R
🖥️ Terminal w/ Vim
🧠 AI (WebLLM, on-device)
⚡ Hybrid kernels
Thanks Bloomberg & all who joined!
youtu.be/7kS_xfKEOmM
Covered:
✨ JupyterLab 4.4, Notebook 7.4
🧪 JupyterLite 0.6
🌐 In-browser Python/R
🖥️ Terminal w/ Vim
🧠 AI (WebLLM, on-device)
⚡ Hybrid kernels
Thanks Bloomberg & all who joined!
youtu.be/7kS_xfKEOmM
Jupyter Frontends & JupyterLite updates | Jupyter Open Studio Day 2025
YouTube video by Jeremy Tuloup
youtu.be
May 28, 2025 at 2:50 PM
Shared some Jupyter Frontends demos last week at Jupyter Open Studio Day (hosted by Bloomberg)!
Covered:
✨ JupyterLab 4.4, Notebook 7.4
🧪 JupyterLite 0.6
🌐 In-browser Python/R
🖥️ Terminal w/ Vim
🧠 AI (WebLLM, on-device)
⚡ Hybrid kernels
Thanks Bloomberg & all who joined!
youtu.be/7kS_xfKEOmM
Covered:
✨ JupyterLab 4.4, Notebook 7.4
🧪 JupyterLite 0.6
🌐 In-browser Python/R
🖥️ Terminal w/ Vim
🧠 AI (WebLLM, on-device)
⚡ Hybrid kernels
Thanks Bloomberg & all who joined!
youtu.be/7kS_xfKEOmM
WebLLM* when?
* As part of the browser's API, obviously
* As part of the browser's API, obviously
Gemma 3n: the 4b LLM that’s up with sonnet-3.7 in chatbot arena
the new innovation is Per-Layer Embeddings, which let it consume dramatically less memory
it was created for phones, and is being rolled out to Android phones soon
developers.googleblog.com/en/introduci...
the new innovation is Per-Layer Embeddings, which let it consume dramatically less memory
it was created for phones, and is being rolled out to Android phones soon
developers.googleblog.com/en/introduci...
June 26, 2025 at 10:54 PM
WebLLM* when?
* As part of the browser's API, obviously
* As part of the browser's API, obviously
Great series of posts by @christianliebel.com on web.dev, covering the capabilities and limitations of LLMs running in the browser, and a walkthrough on building an on-device chatbot.
#WebAI #PromptAPI #WebLLM #GenAI
#WebAI #PromptAPI #WebLLM #GenAI
January 14, 2025 at 10:39 AM
Great series of posts by @christianliebel.com on web.dev, covering the capabilities and limitations of LLMs running in the browser, and a walkthrough on building an on-device chatbot.
#WebAI #PromptAPI #WebLLM #GenAI
#WebAI #PromptAPI #WebLLM #GenAI