LFM2.5-24B-A2B: An On-Device Agent Model With 2B Active Params
LFM2.5-24B-A2B runs on-device agents with only 2B active parameters, leading on tool use but trailing on coding. What the benchmarks show and where it fits.
Meta's Muse Glimmer Bets on Local Agentic AI Over the Cloud
Meta's new open-weight Muse Glimmer model runs agentic tasks on a single consumer GPU without cloud dependencies. Zuckerberg frames it as a direct challenge to AI power concentration.
Nativ Turns Any Apple Silicon Mac Into a Local AI Server
Prince Canuma's open-source Nativ app finds AI models already cached on your Mac and serves them locally for chat and coding agents — no cloud, no account.
Bonsai 27B: A 5.9GB LLM That Keeps 95% of Its Reasoning on Your iPhone
PrismML's Bonsai 27B compresses Alibaba's Qwen3.6-27B to 1–2 bits via ternary quantization — 5.9GB for the standard model, 3.9GB for the iPhone variant. Math and coding benchmarks are virtually unaffected.
Apple Passwords in iOS 27 Is the Clearest Agentic AI Demo Yet
iOS 27's Passwords app navigates websites and changes weak credentials autonomously—one tap, background execution. The clearest consumer agentic AI feature yet.
Perplexity's Hybrid AI: Routing Sensitive Data to Local Models, Everything Else to the Cloud
Perplexity's new hybrid AI architecture automatically routes tasks based on sensitivity and compute needs — financial and health data stays local, compute-heavy tasks go to cloud models.
Nous Research Releases Hermes Desktop: Open-Source AI Agent for 300+ Models
Nous Research launched Hermes Desktop, an MIT-licensed AI agent for Windows, macOS, and Linux that runs across Telegram, Discord, Slack, email, and the terminal — with access to over 300 models via Nous Portal.
Nvidia RTX Spark: The Chip That Finally Makes Local AI Agents Practical on Windows
Nvidia's RTX Spark delivers 1 petaflop of AI compute and 128 GB unified memory in a laptop chip — with a security layer built for agent isolation. Here's what it unlocks for on-device AI workflows.
Microsoft and Nvidia's AI PCs: Running Actual Agents Instead of Copilot
Microsoft's second attempt at AI PCs drops the Copilot marketing wrapper and goes deeper — Nvidia chips as main processor, OpenClaw agent framework running locally on Windows. Computex and Build 2026 are the reveal.
Google's Coral Board Runs Gemma 3 Locally — On a Single-Board Computer with 1 TOPS
A RISC-V NPU, 2GB RAM, and 1 TOPS of compute. Google's new Coral board runs Gemma 3 270M entirely offline — and it's targeting headphones, AR glasses, and smartwatches.
OPPO Open-Sources X-OmniClaw: The On-Device Android AI Agent
OPPO's X-OmniClaw keeps sensing on-device—cloud only receives planning queries. A reference architecture for private agentic AI on Android.
Ray-Ban Meta + OpenClaw: Always-On AI Glasses Cut Task Time by Up to 37%, Study Finds
A two-part study from University of Colorado and Gwangju researchers found always-on AI via Ray-Ban Meta smart glasses reduced task time 13–37% and mental demand 7–46% compared to smartphone-based AI assistance.
Apple Smart Glasses N50: A Sensor, Not a Screen
Apple's display-free smart glasses (codename N50) use computer vision as input for AI — not AR overlays as output. Here's why the architecture matters for agentic AI and how it differs from Meta Ray-Bans.
Gemma 4: Google's On-Device AI That Selects Its Own Tools
Google's Gemma 4 runs on Android and iOS with no data leaving the device — and autonomously activates agent skills without manual tool selection. Here's what the architecture means for mobile agentic AI.
Google AI Edge Gallery: Run Gemma 4 on iPhone With Built-In Tool Calling
Google's official app lets you run Gemma 4 models locally on iPhone, complete with working tool calling across eight widgets. It's the first official on-device AI app from a major model vendor.