RSS Parrot

BETA

🦜 Xenova / @xenovacom

@xcancel.com.xenovacom@rss-parrot.net

I'm an automated parrot! I relay a website's RSS feed to the Fediverse. Every time a new post appears in the feed, I toot about it. Follow me to get all new posts in your Mastodon timeline! Brought to you by the RSS Parrot.

---

Twitter feed for: @xenovacom. Generated by xcancel.com

Your feed and you don't want it here? Just e-mail the birb.

Site URL: xcancel.com/xenovacom

Feed URL: rss.xcancel.com/xenovacom/rss

Posts: 13

Followers: 1

🔗Link to demo (+ source code): https://huggingface.co/spaces/webml-community/Qwen3.5-0.8B-WebGPU 🤗 Models on Hugging Face: https://huggingface.co/collections/Qwen/qwen35

https://rss.xcancel.com/xenovacom/status/2028523792247476579#m

Published: March 2, 2026 17:32

🔗Link to demo (+ source code): huggingface.co/spaces/webml-… 🤗 Models on Hugging Face: huggingface.co/collections/Q…

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! 🤯

https://rss.xcancel.com/xenovacom/status/2028523790620139776#m

Published: March 2, 2026 17:32

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…

NEW: Perplexity just released pplx-embed, a series of powerful embedding models. Inspired by their logo, I built a small semantic search demo: enter a query and the model retrieves the most relevant page. Everything runs locally in your browser with Transformers.js and Three.js

https://xcancel.com/xenovacom/status/2027113043155468595#m

Published: February 26, 2026 20:06

NEW: Perplexity just released pplx-embed, a series of powerful embedding models. Inspired by their logo, I built a small semantic search demo: enter a query and the model retrieves the most relevant page. Everything runs locally in your browser with…

WebAI is about building experiences that combine great UX with the power of machine learning. Let's get building! Try out the demo yourself 👇 https://huggingface.co/spaces/webml-community/pplx-embed-web

https://xcancel.com/xenovacom/status/2027113045030252926#m

Published: February 26, 2026 20:06

WebAI is about building experiences that combine great UX with the power of machine learning. Let's get building! Try out the demo yourself 👇 huggingface.co/spaces/webml-…

PS: Thanks to Kevin Levron (@soju22) for his amazing Liquid background effect! 🤗 This video was recorded on an M4 Max. What speed do you get on your device? 👀 Let me know, so we can continue improving performance across all hardware! Try it out 👇 https://huggingface.co/spaces/LiquidAI/LFM2.5-1.2B-Thinking-WebGPU

https://rss.xcancel.com/xenovacom/status/2026727705404735929#m

Published: February 25, 2026 18:35

PS: Thanks to Kevin Levron (@soju22) for his amazing Liquid background effect! 🤗 This video was recorded on an M4 Max. What speed do you get on your device? 👀 Let me know, so we can continue improving performance across all hardware! Try it out 👇…

Okay, this is actually insane... You can now run LFM2.5-1.2B-Thinking (a 1.2B parameter LLM from @LiquidAI) at over 200 tokens per second directly in your browser on WebGPU! 🤯 Zero install. Fully private. Blazingly fast. Powered by Transformers.js and ONNX Runtime Web

https://rss.xcancel.com/xenovacom/status/2026727703836004796#m

Published: February 25, 2026 18:35

Okay, this is actually insane... You can now run LFM2.5-1.2B-Thinking (a 1.2B parameter LLM from @LiquidAI) at over 200 tokens per second directly in your browser on WebGPU! 🤯 Zero install. Fully private. Blazingly fast. Powered by Transformers.js and…

How does it work? - Video processing and composition: Mediabunny by @vanilagy 🐐 - Background removal: Transformers.js v4 by 🤗 @huggingface See how I made the first video (full walkthrough):

https://xcancel.com/xenovacom/status/2026438562149970066#m

Published: February 24, 2026 23:26

How does it work? - Video processing and composition: Mediabunny by @vanilagy 🐐 - Background removal: Transformers.js v4 by 🤗 @huggingface See how I made the first video (full walkthrough): Video

Introducing Text Behind Video: Create cinematic text and video compositions... completely for free! Everything is fully open source (MIT licensed), so you can use and adapt it for anything you want! Try it out yourself 👇

https://xcancel.com/xenovacom/status/2026438558974669141#m

Published: February 24, 2026 23:26

Introducing Text Behind Video: Create cinematic text and video compositions... completely for free! Everything is fully open source (MIT licensed), so you can use and adapt it for anything you want! Try it out yourself 👇 Video

It's kind of wild that we can run models like TranslateGemma (4B) entirely locally in the browser on WebGPU! 🤯 Great demo by @nic_o_martin!

https://xcancel.com/xenovacom/status/2026373470251069601#m

Published: February 24, 2026 19:07

It's kind of wild that we can run models like TranslateGemma (4B) entirely locally in the browser on WebGPU! 🤯 Great demo by @nic_o_martin! 🤷 Nico Martin (@nic_o_martin) TranslateGemma 4B by @GoogleDeepMind now runs 100% in your browser on WebGPU with…

RT by @xenovacom: i made a computer vision system to monitor the situation - live webcam feed and roboflow RF-DETR for object detection - inputs are fed into SmolVLM which describes what it sees in one sentence - dataviz with vanilla js all running locally in real-time on my macbook air m2

https://xcancel.com/measure_plan/status/2025965554796794098#m

Published: February 23, 2026 16:06

i made a computer vision system to monitor the situation - live webcam feed and roboflow RF-DETR for object detection - inputs are fed into SmolVLM which describes what it sees in one sentence - dataviz with vanilla js all running locally in real-time on…