Getting Started
Everything here is free. No accounts, no cloud services, no subscriptions. These guides walk you through setting up AI tools that run entirely on your own hardware.
Install Ollama & Run Your First LLM
Download Ollama, pull a model, and have a conversation with a local AI in under 5 minutes. No GPU required — runs on CPU.
Voice-to-Text with Whisper
Set up OpenAI's Whisper locally for speech-to-text. Transcribe audio files or use your mic for real-time dictation — all offline.
Block Ads & Trackers with Pi-hole
Turn a Raspberry Pi into a network-wide ad blocker. Every device on your Wi-Fi gets ad-free, tracker-free DNS automatically.
Private Internet with a Travel Router
Set up a GL.iNet router with WireGuard VPN. Encrypt all your traffic on public Wi-Fi — coffee shops, hotels, airports.
Build a Local Model Library
Organize your AI models on fast NVMe storage. Set up Ollama to use external drives, manage multiple model versions, and keep everything portable.
Set Up an Always-On AI Server
Configure a mini PC as a dedicated AI machine. Auto-start Ollama on boot, expose the API to your LAN, and access it from any device.
Local Vision AI with a Webcam
Use a webcam with local vision models for object detection, face recognition, or gesture control — no cloud APIs, no data leaving your machine.
NAS for AI: Training Data & Model Storage
Set up a 2-bay NAS as central storage for your AI lab. Share model files across machines over your LAN.
Fine-Tune a Model on Your Own Data
Take a base model and train it on your writing style, your docs, your domain. LoRA fine-tuning runs on consumer hardware.
Build a Multi-Agent System
Run multiple AI agents with different roles — one for code, one for research, one for memory. Orchestrate them locally with a shared context.
Recommended Stacks
Not sure what to buy? Here's what we'd put together at each budget level. Each stack is built around a specific model size — the bigger the model, the smarter the AI.
🟢 Starter — 3B Models ($150–250)
- Raspberry Pi 5 16GB Kitcompute — runs 3B models
- USB Condenser Micvoice input for Whisper STT
- Webcam Privacy Covers (6-pack)hardware privacy
🔵 Core — 7B Models ($430–550)
- GMKtec M5 Ultra (32GB)compute — runs 7B-8B models smoothly
- NVMe SSD Enclosure 10Gbpsportable model storage
- USB Condenser Micvoice input for Whisper STT
- GL.iNet Mangoprivate networking
🟣 Pro — 13B+ Models ($800–1,100)
- GMKtec K11 Pro (Ryzen 9, 32GB DDR5)compute — handles 13B+ and quantized 70B
- Samsung 990 Pro 1TB NVMefast internal model storage
- USB4 NVMe Enclosure 40Gbpsexternal model overflow
- TONOR TC-777 Micquality voice input
- GL.iNet Beryl AXVPN travel router
- USB-C Hub 7-in-1connect everything
🔴 Lab — Multi-Device AI Network ($1,500+)
- MinisForum Venus UM790 Proprimary AI server (Zen4, 32GB DDR5)
- Jetson Orin Nano Superdedicated edge AI / vision processing
- Synology DS223j + 2x HDDcentral NAS for models & datasets
- Pi-hole Privacy DNS Kitnetwork-wide ad blocking
- GL.iNet Slate AXVPN gateway for the lab
- Logitech C920s Provision AI input
- Keychron V1 QMKprivacy keyboard (open firmware)
Ready to build your stack? Every product is available in our store.
Browse Products →