RSS Parrot

R to @xenovacom: I can't wait to see what the community builds with it! 🤗 Links: 📄 Blog post: https://huggingface.co/blog/ibm-granite/granite-4-nano 🚀 Demo (+ source code): https://huggingface.co/spaces/ibm-granite/Granite-4.0-Nano-WebGPU

https://xcancel.com/xenovacom/status/1983218722006249759#m

Published: October 28, 2025 17:06

I can't wait to see what the community builds with it! 🤗 Links: 📄 Blog post: huggingface.co/blog/ibm-gran… 🚀 Demo (+ source code): huggingface.co/spaces/ibm-gr…

IBM just released Granite-4.0 Nano, their smallest LLMs ever (300M & 1B)! 😍 The models demonstrate remarkable instruction following and tool calling capabilities, and can even run locally in-browser! This means they can interact with websites and call browser APIs for you! 🤯

https://xcancel.com/xenovacom/status/1983218720366326002#m

Published: October 28, 2025 17:06

IBM just released Granite-4.0 Nano, their smallest LLMs ever (300M & 1B)! 😍 The models demonstrate remarkable instruction following and tool calling capabilities, and can even run locally in-browser! This means they can interact with websites and call…

R to @xenovacom: Just remember: nanochat isn't meant to be the most powerful LLM out there. Rather, it's designed as an educational resource to show you how to build a full-stack LLM from start to finish (< $1000). Enjoy! 🤗 Try it out yourself (+ source code): https://huggingface.co/spaces/webml-community/nanochat-webgpu

https://xcancel.com/xenovacom/status/1980399603762754042#m

Published: October 20, 2025 22:23

Just remember: nanochat isn't meant to be the most powerful LLM out there. Rather, it's designed as an educational resource to show you how to build a full-stack LLM from start to finish (< $1000). Enjoy! 🤗 Try it out yourself (+ source code):…

BOOM! 💥 Today I added WebGPU support for @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 😅

https://xcancel.com/xenovacom/status/1980399601812389908#m

Published: October 20, 2025 22:23

BOOM! 💥 Today I added WebGPU support for @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…

R to @xenovacom: 🔗 Demo + source code: https://huggingface.co/spaces/ibm-granite/granite-docling-258M-WebGPU

https://xcancel.com/xenovacom/status/1975648963865747784#m

Published: October 7, 2025 19:46

🔗 Demo + source code: huggingface.co/spaces/ibm-gr…

Introducing Granite Docling WebGPU 🐣 State-of-the-art document parsing 100% locally in your browser! 🤯 🔐 No data sent to a server (private & secure) 💰 Completely free... forever! 🔂 Docling ecosystem enables conversion to HTML, Markdown, JSON, and more! Try out the demo! 👇

https://xcancel.com/xenovacom/status/1975648512009511166#m

Published: October 7, 2025 19:44

Introducing Granite Docling WebGPU 🐣 State-of-the-art document parsing 100% locally in your browser! 🤯 🔐 No data sent to a server (private & secure) 💰 Completely free... forever! 🔂 Docling ecosystem enables conversion to HTML, Markdown, JSON, and more! …

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!

https://rss.xcancel.com/xenovacom/status/1973784183492485277#m

Published: October 2, 2025 16:16

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…

R to @xenovacom: 🗂️ Model collection: https://huggingface.co/collections/ibm-granite/granite-40-language-models-6811a18b820ef362d9e5a82c 🔗 WebGPU demo + source code: https://huggingface.co/spaces/ibm-granite/Granite-4.0-WebGPU

https://rss.xcancel.com/xenovacom/status/1973784185589662067#m

Published: October 2, 2025 16:16

🗂️ Model collection: huggingface.co/collections/i… 🔗 WebGPU demo + source code: huggingface.co/spaces/ibm-gr…

RT by @xenovacom: Do you remember #Jarvis, the AI Assistant from Iron Man? I just built one entirely in #JavaScript as an #MCP-Client powered by #TransformersJS. It's a local-first assistant that runs completely in the browser on your machine. No API calls, no cloud dependency!

https://rss.xcancel.com/nic_o_martin/status/1972958416198160765#m

Published: September 30, 2025 09:35

Do you remember #Jarvis, the AI Assistant from Iron Man? I just built one entirely in #JavaScript as an #MCP-Client powered by #TransformersJS. It's a local-first assistant that runs completely in the browser on your machine. No API calls, no cloud…

RT by @xenovacom: Transformers.js lets you run AI models offline in the browser with ONNX + WebGPU. Build a chatbot with Llama 3.2, optimize performance, and try local AI tasks like object detection & background removal.

https://xcancel.com/BetterStackHQ/status/1972671423492530521#m

Published: September 29, 2025 14:34

Transformers.js lets you run AI models offline in the browser with ONNX + WebGPU. Build a chatbot with Llama 3.2, optimize performance, and try local AI tasks like object detection & background removal.