STARBOY perceives its environment through a camera, microphone, temperature... sensor, and accelerometer. We trained multiple tiny image models that run locally on the device, letting it recognize human faces and hand gestures.show more

This is not an EMB wristband!! It’s a neural... network trained on hand gestures using only magneto and accelerometer sensors. It works on many existing smartwatches. Sometimes simpler is bettershow more

Run Uncensored Qwen-Image 2.1 on 16GB Mac Qwen's image... model with no filters makes the images cloud apps refuse and your prompts never leave your Mac, all of it done locally Run AI models locally ->show more

Meet “Reachy on Wheels” Presented at #PyTorchConf and created... by Ian Ballantyne and Xavier Plantaz, this Reachy Mini is powered by on-device Gemma models to talk, listen, and autonomously navigate its environment. The entire system is battery-powered and runs locally. No cloud connection required.show more

wow.. ComfyUI's node canvas is crazy we can now... generate image, video, audio, even 3D models locally on the AI canva and.. it has all the top AI models like FLUX, GPT image, Kling, Veo, Hunyuan3D and more step by step tutorial:show more

Simulate an Unmanned Aerial Vehicle (UAV) using camera and... lidar sensor models to deliver a package while navigating a city environment and avoiding obstacles 🛫 🔗show more

In this setup, a Blender blockout provides the motion... and composition while a reference image guides the environment, subject, and textures with MiniMax H3. With open weights, you can previs the final look locally for free or run it on Comfy Cloud. To try this workflow, link below 👇show more

Okay so I made a ScrollController that instead of... gestures uses accelerometer (includes gravity!) and basic physics for friction and movement and it’s funny! #Fluttershow more

STARBOY has moods and emotions: stress it out in... a loud environment and it gets anxious and has to calm down. Leave it in the cold and it shivers. Shake it enough and it gets dizzy and mad at you. Each device ships with a distinct personality out of the box.show more

Gemma 3n can run locally on 2gb ram devices.... Let that sink in. Holy moly, and its multimodal.show more

I had an early access to GPT-6 Astra and... I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in Blender with geometry that you can manually tweak and run 60fps as a locally rendered "game" on device.show more

Jungkook's new camera can zoom in and out with... hand gestures.show more

Local Laya blitzed other models on RTX 4090 ⚡️... Four local decision models raced down Wikipedia picking out every word that names a centipede and Laya took 3.9 ms a word so it ended up being the fastest overall Run decision models locally ->show more

Tiny Recursive Models: A tiny 7M parameter model that... recursively refines its answer beats LLMs 100x larger on hard puzzles like ARC-AGI We independently reproduced the paper, corroborated results, and released the weights + API access for those looking to benchmark it 🔍show more

Run Ternary Bonsai 2 locally in Atomic Chat 🪴... PrismML shrank Qwen3.5 7x so the 9B goes from 17.9 GB to just 2.42 GB and it keeps up or outperforms the original model on benchmarks Run AI models locally ->show more

ABot World 0.5B is out! we have now world... models at home, running in real-time on consumer GPU feed it an initial image, steer it with with your keyboard 🌎 you can run it locally or play now on spaces ▶️show more

LM Studio 0.3.4 ships with Apple MLX 🚢🍎 Run... on-device LLMs super fast, 100% locally and offline on your Apple Silicon Mac! Includes: > run Llama 3.2 1B at ~250 tok/sec (!) on M3 > enforce structured JSON responses > use via chat UI, or from your own code > run multiple models simultaneously > download any model from Hugging Face Video at 1x speed.show more

Running MiniCPM5-2B locally on a 16GB MacBook 💻 It... beats Qwen3.5-4B on benchmarks, so we asked it to find recent AI news, it called web search, pulled back 10 results and summarized the key developments inside Atomic Chat Run local models viashow more