Privacy

I’ve been running AI models locally for about a year now, and it completely changed how I think about privacy. Every word I type stays on my machine — no servers, no telemetry, no third parties.

Cloud tools like ChatGPT and Claude are powerful, but many services store your input on remote servers. That trade-off bothered me when working with sensitive code or private documents, so I started exploring local AI.

Why Go Local?

• Absolute Privacy: My prompts never leave my machine. No data goes to any cloud provider, period.
• No Recurring Costs: After the initial hardware investment, running models is free.
• Offline Capability: I’ve used local AI on flights and during internet outages. It just works.
• Full Control: Run any open-source model without rate limits or usage caps.

What I Actually Use It For

This isn’t just theory — I use local AI daily in two practical ways:

Speech-to-text on My Mac: I have a local model on my Mac for speech-to-text. I speak, it writes — that’s how I’m writing this post right now.

News Summarization on My iPhone: I run a small model as an iPhone app. Long articles get fed in, and I get a clean 150-200 word summary. Fully offline.

Model Sizes

The “B” stands for billions of parameters — more is generally smarter, but needs more hardware.

• 7B (Llama 3 8B, Mistral 7B): My go-to. Runs on consumer hardware, handles summarization, coding, and conversation well.
• 13B (Llama 2 13B, CodeLlama 13B): Smarter, especially for complex reasoning and longer code. Needs more VRAM.
• 70B (Llama 2 70B): Approaching cloud-level quality, but requires 48GB+ VRAM or heavy quantization.
• 141B total / 22B active (Mixtral 8x22B): A Mixture-of-Experts model with 8 experts — uses ~22B parameters per forward pass. Requires 48GB+ VRAM or heavy quantization.

VRAM Requirements

• 8GB: Sweet spot for quantized 7B models — what I started with.
• 16GB: Handles 13B models and some quantized 30B models.
• 24GB+: Unlocks larger quantized models and 13B at full precision.
• 48GB+: 70B models become accessible, especially on Apple Silicon with unified memory.

Getting Started

1. Install Ollama: Head to ollama.com and download the installer. Takes about two minutes.
2. Pull your first model: Run ollama run llama3 in a terminal. Downloads the 8B model (~4.7GB) and starts chatting. That’s it.
3. Add a web interface: Run docker run -d -p 3000:8080 ghcr.io/open-webui/open-webui:main and open http://localhost:3000 for a ChatGPT-like experience.
4. Explore: Try ollama pull mistral or ollama pull codellama for different use cases.

Troubleshooting

Running on CPU instead of GPU? On Linux, install NVIDIA drivers first. Out of memory? Try a smaller model or Ollama’s :q4_0 tag for lighter quantization. Everything runs fully offline once downloaded.

Personal Take

Local AI shines for sensitive data, offline work, and experimenting without API costs. That said, I still use cloud AI when I need the latest models or large context windows — it’s not either-or.

Note: Hardware prices and model availability may change. Always check current pricing before purchasing.

Disclosure: Some links in this post may be affiliate links. I may earn a commission at no extra cost to you.

💻 Hardware Recommendation: To run local LLMs smoothly, you’ll need a GPU with at least 16GB of VRAM or an Apple Silicon Mac. See my GPU Buying Guide for recommendations.

Why I Started Taking VPNs Seriously

I used to think VPNs were overhyped — “I’m not doing anything illegal,” I’d say. But after digging into how the internet actually works, my perspective shifted completely.

Data breaches continue to expose billions of records each year. Your ISP can see every website you visit. Advertisers track you across the web. On public WiFi, your data is practically an open book.

I’ve been using VPNs for over three years now, and it’s one of the easiest privacy wins you can get.

How a VPN Works

Think of a VPN as an encrypted tunnel for your internet traffic. When you connect to a VPN server, your data goes to the VPN first, which encrypts everything and forwards it to the website. Your ISP sees only that you’re connected to a VPN — not what you’re doing. The website sees the VPN’s IP, not yours.

It’s that simple. A privacy buffer between you and the rest of the internet.

Real Scenarios Where a VPN Helped Me

Public WiFi — Working from a hotel, my traffic was encrypted end-to-end. Without a VPN, anyone on that network could have intercepted my credentials.

Traveling abroad — A VPN let me access streaming content blocked in certain countries.

ISP tracking — My ISP was tracking my browsing habits. After switching to a VPN, my traffic became invisible to them.

VPN Myths Worth Busting

“VPNs make you completely anonymous” — No. They hide traffic from your ISP, but the VPN provider can still see your data. That’s why choosing a reputable one matters.

“Free VPNs are just as good” — Be careful. Many free VPNs sell your data — the exact thing you’re trying to prevent.

“You only need one for illegal stuff” — Privacy is a right, not a suspicion.

My Top VPN Picks

NordVPN — My daily driver. Fast speeds, strict no-logs policy independently audited, 6,000+ servers in 60+ countries, and a clean app with no learning curve.

Other solid options:

• ExpressVPN — Excellent speeds, pricier
• Surfshark — Budget-friendly with unlimited devices
• ProtonVPN — Best free tier to try before you buy

Disclosure: This post contains affiliate links. I may earn a commission at no extra cost to you. I only recommend VPNs I’ve personally used and trust.

My Take

Don’t wait for a breach to happen to you. A VPN is the simplest, most affordable step toward better online privacy. Set it up today — it takes minutes and protects your whole family.

Note: Prices, discounts, and offers mentioned in this post may change. Please check the provider’s website for current pricing.