Guides & Resources
Learn how to run AI models locally on your Apple devices. From beginner tutorials to advanced optimization techniques, our guides help you get the most out of local AI.
Start here
New to local AI? Install Ollama, then learn how much memory your first model actually needs.
- How to Run AI Models Locally with OllamaQuick start guide for installing Ollama, selecting models, and running your first local LLM on macOS.6 min read
- How Much RAM Do You Need for a Local LLM?The model-size-to-memory matrix: ~0.6 GB per billion parameters at Q4. What each RAM tier from 8GB to 128GB actually runs, with Q4/Q8 sizes and the top pick per tier.7 min read
Device guides
Pick the right model for your exact hardware: MacBook, iPhone, or that 8GB Mac you already own.
- Best Local LLM Models for MacBook in 2026Comprehensive guide covering MacBook Air vs Pro, M1-M5 chip comparison, and which AI models to run on your Apple Silicon Mac.10 min read
- Best LLM Models for iPhone in 2026Complete guide to running AI models on iPhone. Learn which models work best, RAM limitations, speed expectations, and step-by-step Ollama setup.8 min read
- Can an 8GB Mac Run an LLM?Yes, with the right model. Engine-derived picks that fit an 8GB memory budget, what an 8GB Mac cannot run, and when 16GB is worth it.6 min read
Use cases
Local AI for real work: coding assistants ranked by RAM, and image generation on Apple Silicon.
- Best Local LLM for Coding (2026): Ranked by RAMThe local coding tier list: Qwen3.6 27B, Devstral Small 2 and more with sourced benchmark scores, plus continue.dev, aider and Zed setup.10 min read
- Local Image Generation on Mac: What Fits Your RAMFLUX, SDXL and SD 3.5 on Apple Silicon: which image models fit 8-64GB RAM, with HuggingFace-verified file sizes and the best apps.9 min read
Privacy & offline
What local inference really keeps on your device, and how to run AI with zero network access.
- Is Local AI Actually Private?What stays on your device with local inference, what still touches the network, and how to make a local AI setup fully airtight.7 min read
- How to Run AI Completely Offline on Your DeviceLearn why offline AI matters for privacy, how to set up completely private AI with no internet required.5 min read
Under the hood
How the runtime actually works once a model is loaded.
Quick links
- Requirements CalculatorEnter your RAM or VRAM, see what you can run
- All DevicesBrowse all supported Macs and iPhones
- MacBook Air ModelsBest AI models for MacBook Air M1-M5
- MacBook Pro ModelsBest AI models for MacBook Pro M1-M5
- iPhone 16 Pro ModelsMobile AI models for iPhone
- iPhone AI Models HubEvery supported iPhone, iPhone 14 to 17
- ModelFit WizardGet personalized recommendations