# Guides: AI recorders, local AI and mini PCs

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.

## AI recorders

Learn how to record calls and online meetings, how free transcription allowances work and what to check before sharing a recording. Our setup guides keep hardware recording separate from the cloud services that turn speech into searchable notes.

- [Does Plaud need a subscription? Plans and free minutes explained](https://testbenchlab.com/guides/does-plaud-need-a-subscription/) — explainer, 2 min
- [Does Pocket AI need a subscription? What is free and what is not](https://testbenchlab.com/guides/does-pocket-ai-need-a-subscription/) — explainer, 2 min
- [How to record a Microsoft Teams meeting](https://testbenchlab.com/guides/how-to-record-a-teams-meeting/) — how-to, 2 min
- [How to record a phone call on iPhone (built-in, apps and AI recorders)](https://testbenchlab.com/guides/how-to-record-a-phone-call-on-iphone/) — how-to, 2 min
- [How to record a Zoom meeting (and get an AI transcript)](https://testbenchlab.com/guides/how-to-record-a-zoom-meeting/) — how-to, 2 min
- [How to use the Plaud Note Pro: setup to first summary](https://testbenchlab.com/guides/how-to-use-plaud-note-pro/) — how-to, 2 min
- [Is Plaud HIPAA compliant?](https://testbenchlab.com/guides/is-plaud-hipaa-compliant/) — explainer, 2 min
- [One-party vs two-party consent states: can you use an AI recorder?](https://testbenchlab.com/guides/recording-consent-laws-by-state/) — explainer, 3 min

## 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.

- [How much RAM do you need to run a local LLM?](https://testbenchlab.com/guides/how-much-ram-for-local-llm/) — explainer, 2 min
- [How to install Ollama on Windows 11 (Ryzen AI mini PC)](https://testbenchlab.com/guides/install-ollama-windows-11-ryzen-ai-mini-pc/) — how-to, 2 min
- [llama.cpp with Vulkan on a Radeon iGPU](https://testbenchlab.com/guides/llama-cpp-vulkan-radeon-igpu/) — how-to, 2 min
- [Run local LLMs on the Ryzen AI NPU with Lemonade Server](https://testbenchlab.com/guides/run-llms-on-ryzen-ai-npu-lemonade-server/) — how-to, 2 min

## AI PC hardware

Understand NPUs, unified memory, integrated graphics and external GPU connections. The goal is to translate specifications into decisions: how large a model you can load, whether a particular backend supports your chip and what expansion would cost.

- [Mini PC vs Mac mini for AI](https://testbenchlab.com/guides/mini-pc-vs-mac-mini-for-ai/) — explainer, 2 min
- [NPU vs GPU: which runs AI better on a mini PC?](https://testbenchlab.com/guides/npu-vs-gpu/) — explainer, 2 min
- [NVIDIA DGX Spark vs Strix Halo mini PCs](https://testbenchlab.com/guides/dgx-spark-vs-strix-halo/) — explainer, 2 min
- [Radeon 890M vs Radeon 8060S: what the iGPU means for AI and gaming](https://testbenchlab.com/guides/radeon-890m-vs-radeon-8060s/) — explainer, 2 min
- [Ryzen AI 9 HX 470 vs HX 370: what changed?](https://testbenchlab.com/guides/ryzen-ai-9-hx-470-vs-hx-370/) — explainer, 2 min
- [Ryzen AI Max+ 395 (Strix Halo) explained](https://testbenchlab.com/guides/ryzen-ai-max-395-strix-halo-explained/) — explainer, 2 min
- [What is an AI PC? (and is a Copilot+ PC different?)](https://testbenchlab.com/guides/what-is-an-ai-pc/) — explainer, 2 min
- [What is an NPU, and does your PC need one?](https://testbenchlab.com/guides/what-is-an-npu/) — explainer, 2 min
- [What is OCuLink? OCuLink vs USB4 for an external GPU](https://testbenchlab.com/guides/what-is-oculink/) — explainer, 2 min
- [What is unified memory, and why does it matter for local AI?](https://testbenchlab.com/guides/what-is-unified-memory/) — explainer, 2 min