Guides · 22 articles

Guides

Clear guides to recording conversations and running AI on your own computer. Start with the task you want to complete, then choose the hardware or software that supports it.

FeaturedHOW-TO · 2 MIN How to install Ollama on Windows 11 (Ryzen AI mini PC) Install Ollama, run a small model and check which processor is used. A successful response does not prove Radeon acceleration. Current documentation includes a Vulkan route for additional GPU support. David Wilson · updated 02.10.26Read →
EXPLAINER · 2 MINAI RECORDERS Does Plaud need a subscription? Plans and free minutes explained You can use Plaud without a paid subscription within its included transcription allowance.
EXPLAINER · 2 MINAI RECORDERS Does Pocket AI need a subscription? What is free and what is not Pocket’s current product site says core features and unlimited minutes do not require a subscription.
EXPLAINER · 2 MINLOCAL AI How much RAM do you need to run a local LLM? Budget local-model memory for weights, context cache and runtime, not just the download.
HOW-TO · 2 MINAI RECORDERS How to record a Microsoft Teams meeting In a supported Teams meeting, open More actions, choose Record and transcribe, then start recording.
HOW-TO · 2 MINAI RECORDERS How to record a phone call on iPhone (built-in, apps and AI recorders) Use iPhone’s built-in call recording when it is available for your device, language and region.
HOW-TO · 2 MINAI RECORDERS How to record a Zoom meeting (and get an AI transcript) Use Zoom’s recording controls to capture a meeting, then obtain a transcript through the supported cloud feature or an approved transcription service.
HOW-TO · 2 MINAI RECORDERS How to use the Plaud Note Pro: setup to first summary Set up Plaud Note Pro in the official app, make a short recording and check the full capture-to-summary workflow before relying on it.
EXPLAINER · 2 MINAI RECORDERS Is Plaud HIPAA compliant? Plaud states that it supports HIPAA compliance and now provides instructions for requesting a signed Business Associate Agreement.
HOW-TO · 2 MINLOCAL AI llama.cpp with Vulkan on a Radeon iGPU Vulkan is a useful llama.cpp route for Radeon integrated graphics.
EXPLAINER · 2 MINAI PC HARDWARE Mini PC vs Mac mini for AI Choose a mini PC for a Windows or Linux workflow and a Mac mini for software built around macOS and Apple silicon.
EXPLAINER · 2 MINAI PC HARDWARE NPU vs GPU: which runs AI better on a mini PC? For general local-model experimentation, start with a supported GPU backend.
EXPLAINER · 2 MINAI PC HARDWARE NVIDIA DGX Spark vs Strix Halo mini PCs Choose DGX Spark for a supported CUDA-focused development workflow.
EXPLAINER · 3 MINAI RECORDERS One-party vs two-party consent states: can you use an AI recorder? One-party consent generally means one participant can consent to recording; all-party consent generally requires every participant’s permission.
EXPLAINER · 2 MINAI PC HARDWARE Radeon 890M vs Radeon 8060S: what the iGPU means for AI and gaming Radeon 8060S belongs to the larger Strix Halo graphics tier, while 890M belongs to the smaller Ryzen AI 9 tier.
HOW-TO · 2 MINLOCAL AI Run local LLMs on the Ryzen AI NPU with Lemonade Server Lemonade provides local model tools for several backends, including supported Ryzen AI routes.
EXPLAINER · 2 MINAI PC HARDWARE Ryzen AI 9 HX 470 vs HX 370: what changed? HX 470 refreshes the HX 370 platform with higher headline clocks and NPU capability.
EXPLAINER · 2 MINAI PC HARDWARE Ryzen AI Max+ 395 (Strix Halo) explained Strix Halo is the common name for AMD’s Ryzen AI Max platform.
EXPLAINER · 2 MINAI PC HARDWARE What is an AI PC? (and is a Copilot+ PC different?) AI PC is a broad description for a computer offering AI-related hardware or software.
EXPLAINER · 2 MINAI PC HARDWARE What is an NPU, and does your PC need one? An NPU is a specialised processor for supported AI operations.
EXPLAINER · 2 MINAI PC HARDWARE What is OCuLink? OCuLink vs USB4 for an external GPU OCuLink carries PCIe outside a system and is often used for an external GPU dock.
EXPLAINER · 2 MINAI PC HARDWARE What is unified memory, and why does it matter for local AI? Unified memory is a shared physical pool that multiple processors can access.

Local AI

Install a model runner, choose a model that fits your memory and check which processor is actually doing the work. These guides cover Ollama, Lemonade and llama.cpp, with particular attention to AMD integrated graphics and Ryzen AI hardware.