#edge AI
8 stories taggededge AI.
Liquid AI Releases Two Open-Weight Decision Models That Answer in Under 50 Milliseconds on Edge Hardware
The d1-3B and d1-omni-600M models skip word-by-word generation and return structured answers in a single calculation, fast enough to run on a $250 Jetson Orin Nano board.
NVIDIA's new Jetson Orin Nano 2 chip aims to put frontier AI inside drones and home robots
The tiny computer uses 40% less power than its predecessor while doubling AI processing speed, and NVIDIA says developers will be able to run frontier-grade intelligence directly inside physical machines.
Liquid AI Squeezes Its Small Models onto Phones and Raspberry Pis Without Losing Much Quality
A new training trick called Quantization-Aware Distillation lets Liquid AI's compact language models run on cheap hardware while keeping 97% of their full-precision accuracy.
Liquid AI's LFM2.5-VL-3B Can Run on Your Phone and Still Read Your Screen
The new 3-billion-parameter vision model fits in 3 GB of memory, beats larger rivals on screen-reading benchmarks, and runs fast enough on a smartphone to be genuinely useful.
This Four-Legged Robot Inspects Factories Using AI, No Cloud Connection Needed
Avnet and Weston Robot have built a dog-like inspection robot that thinks for itself on-site, spots problems in real time, and works even when the internet is not available.
Liquid AI's new 2.6B model runs AI agents directly on your laptop or phone
LFM2.5-2.6B is a compact AI model that can handle multi-step tasks without sending your data to the cloud, and it competes with models four times its size on key benchmarks.
Shining Light onto a Chip Could Give Robots a Faster AI Brain Update
Cornell Tech researchers have built a receiver that rewrites a chip's memory using flashes of light instead of electrical wires, and it could one day let warehouse robots refresh their AI models on the fly.
NASA Ran a Google AI Model Inside a Satellite. Here Is What It Found.
A small, efficient AI model analyzed real images from orbit and sent back plain-text descriptions instead of raw data. It could cut wildfire alerts from 90 minutes to near-instant.