Total Beginners Guide to Local AI on Mac

█▀█ █▀▀ ▄▀█ █▀▄ █▀▄▀█ █▀█ █▀█ █▀▀ █▀▄ ██▄ █▀█ █▄▀ █ ▀ █ █▄█ █▀▄ ██▄ The era of renting intelligence from Silicon Valley is over. This video provides a comprehensive guide for CEOs and founders on setting up local AI agents on a Mac, moving away from the SaaS subscription model toward personal software ownership. We cover everything from hardware specifications to the nuances of local model serving. Key Takeaways: Hardware Priority: Why RAM is more important than CPU for local AI tasks. Model Selection: Navigating Hugging Face and understanding MLX quantisation. The Stack: How to use Ollama, LM Studio, and OMLX to serve models. Agent Harnesses: Setting up Open Code and Claude Code for local workflows. Performance Reality: Managing thermals and understanding the speed trade-offs of local vs cloud. Code examples and config +: terminal cheat sheet https://samuelgregory.co.uk/videos/to... Ollama: https://ollama.com/ LM Studio: https://lmstudio.ai/ oMLX: omlx.ai Warp: https://samuelgregory.co.uk/warp Huggingface: https://huggingface.co/ Work with me: https://samuelgregory.co.uk Hardware: 14 inch M5 Max MacBook Pro 128GB RAM 40 Core GPU 2TB SSD Harness: OpenCode / Claude Code Server: oMLX --- Support the content:   / 0x5am5   Twitter: @0x5am5 $ cat tools.txt ──────────────────────────────── Kilo: https://samuelgregory.co.uk/kilo-code Replit (Favourite Vibe Code Tool) : https://samuelgregory.co.uk/replit Perplexity (deep research): https://samuelgregory.co.uk/perplexity Claude Code: https://claude.ai/api/referral/jZ9vnM... Warp Terminal: https://samuelgregory.co.uk/warp ⚒️ more at https://samuelgregory.co.uk/tools $ cat services.txt ──────────────────────────────── Domain Names: https://samuelgregory.co.uk/namecheap Hosting: https://www.hostg.xyz/aff_c?offer_id=... Online Storage ($200 credit): https://samuelgregory.co.uk/digital-o... ⚒️ more at https://samuelgregory.co.uk/tools $ cat gear.txt ──────────────────────────────── Sony A7c II: https://amzn.to/40qaYEJ Lens Sigma 16-28mm: https://amzn.to/3IaDzqx Microphone Samson QU2: https://amzn.to/3TkshCE Macbook Pro M1 Max: https://amzn.to/48736M6 $ cat books.txt ──────────────────────────────── The Full Stack Agency: https://flowst8.dev/store Lingo: Agile: https://thefullstackagency.gumroad.co... Lingo: Startup: https://thefullstackagency.gumroad.co... $ cat timestamps.txt ──────────────────────────────── 00:00 Getting started with local AI on a Mac 01:10 Which Mac to buy (Chip, RAM, form-factor) 01:54 How much RAM do you get 05:06 M-series chips (base, Pro, or Max?) 07:49 Getting started with Open Source models 08:16 Model parameter size 08:50 Quantizations 09:56 Dense and Mixture of Experts (MoE) variants 11:20 Context 12:22 Model formats (MLX vs GGUF vs AWQ) 14:40 Choosing your model 16:13 Downloading and running a model 16:48 Ollama 17:38 Model size variants 19:14 LM Studio 20:46 oMLX 21:15 MLX LM (the Apple way to run MLX models) 21:45 Downloading your LLM in oMLX 22:41 Setting specific model settings (Context window, TopP, temperature, recommended settings) 23:26 Lowering context to run larger models 23:50 Serving a local model in oMLX 25:15 Setting up local AI in a harness 25:54 Configuring OpenCode 29:38 The terminal 33:20 Using our model OpenCode 34:07 Prompt processing, RAM usage, 35:20 Setting up local AI in harness (Pi) 36:57 Using your local AI model 37:16 Temperature and open app considerations 38:02 I need your help to make this tutorial better! #LocalAI #Mac #LocalLLM