Tom Fenton moves from local AI concepts to hands-on tools for matching LLMs to hardware, running local chatbots with Ollama and benchmarking AI performance.

Learn how to run a 32B local LLM on a $599 Mac Mini using Ollama. This setup reduces cloud AI costs while maintaining strong ...

Tom Fenton explains how local AI fits into the broader private AI discussion for VMware environments, distinguishing enterprise-scale private AI deployments from smaller local AI setups running on ...

These third-party projects greatly expand the ways agents and LLMs can draw on facts, documents, and conversations to deliver ...

The big picture: Microsoft is easing one of the strict lines it previously drew around Copilot+ PCs, allowing more Windows 11 machines to run local AI workloads with the right GPU. An update shows ...

Open source vision language model JoyAI-VL-Interaction from JD.com watches live video streams and speaks without being ...

Amazon Alexa on-device AI now runs in millions of Echo homes, but Panos Panay’s July 2026 CNBC interview reveals the split: ...

Meta’s new smart glasses will ship with Muse Spark, a compact AI model the company describes as purpose-built for wearable ...

Phi-4 14B through Ollama was the best local performer in this project, combining correct answers with usable response times. Copilot remained faster and smoother on the same benchmark prompts, while ...

Rather than generating text word by word, Google's experimental open-source model drafts entire passages simultaneously using diffusion, resulting in up to 4x faster inference.

I gave Claude access to my Home Assistant. It helped me audit, debug, and improve my smart home better than I ever could have.

Visual Studio Code 1.126 adds session-level Copilot cost information, continuing Microsoft's recent focus on helping developers monitor and manage usage-based GitHub Copilot billing.