AMD Unveils Threadripper Halo Station to Challenge Nvidia
AMD showed off a liquid-cooled workstation at IFA 2026 that it says can run AI models with more than a trillion parameters locally, without a cloud connection.
Read more →On-Device AI
On-device AI runs machine-learning models directly on a phone, laptop, or chip, without sending data to the cloud. It can improve privacy, work offline, and reduce latency, and it underpins features like Apple Intelligence and small local models. This hub gathers news and explainers on on-device AI and the compact models that make it possible.
Combine with:
Perplexity Launches Hybrid Compute to Keep AI Tasks Private on Mac
Perplexity's new Hybrid Compute feature splits AI agent tasks between the cloud and a local model on Apple silicon Macs, keeping sensitive data on-device.
Read more →Samsung Unveils xMAE and HiMAE AI Models for Wearables
Samsung Research introduced xMAE and HiMAE, two on-device AI models that read heart and sleep signals from wearables in under a millisecond, with papers accepted at ICML and ICLR 2026.
Read more →Meta Releases Muse Glimmer, a 30B Open-Weight AI Agent Model
Meta released Muse Glimmer, a 30-billion-parameter open-weight model that runs AI agents locally on a single consumer GPU, under an Apache 2.0 license.
Read more →Liquid AI Releases LFM2.5-2.6B, an On-Device AI Agent Model
Liquid AI has released LFM2.5-2.6B, an open-weight model small enough to run on a phone or laptop while handling multi-step AI agent tasks offline.
Read more →
What Is an AI PC — and What Makes a Laptop 'AI-Ready'?
An AI PC pairs a normal processor with a dedicated NPU chip that runs AI features like transcription, translation, and image generation locally, without sending data to the cloud.
Read more →
What Is Apple Intelligence — and How Does It Work?
Apple Intelligence is Apple's built-in AI system for iPhone, iPad, and Mac — a mix of on-device models and a private cloud service that Apple says even it can't access.
Read more →Syntiant Files for Nasdaq IPO to Scale 'Physical AI' Chips
Intel- and Microsoft-backed chipmaker Syntiant filed to list on Nasdaq under ticker SYTN, betting on demand for its low-power, on-device 'Physical AI' processors.
Read more →What Is On-Device AI — and Why It Matters
On-device AI runs machine learning models directly on your phone, laptop, or chip — without sending data to the cloud. It is the technology behind Apple Intelligence, Google Gemini Nano, and a new wave of ultra-small models like Liquid AI's LFM2.5-230M.
Read more →Liquid AI Ships 230M Open Model for On-Device AI Agents
Liquid AI released LFM2.5-230M, a 230-million-parameter open-weight model that runs AI agent tasks at 213 tokens per second on a phone CPU and 42 tokens per second on a Raspberry Pi — without a cloud connection.
Read more →