Learn.
Plain answers about earning with a Mac, running AI on Apple Silicon and how MLX Network works. Every outside number links to its source.
Get started
Start earning MLX on your Mac.Set up MLX Node, link your wallet, choose when your Mac works and watch it mine MLX Tokens. How hourly rewards are scored, locked and shown in your wallet.Read the guideCreate your MLX wallet.How to create an MLX wallet at wallet.mlx.app step by step: pick a name, save a passkey, back up your 24-word recovery phrase, set auto-lock and link your Mac.Read the guideHow to use MLX Harness.A guide to MLX Harness, our free Mac app for running AI models locally: download models, chat, agents and tools, image generation and a local OpenAI-style API.Read the guide
Earn with your Mac
Mining crypto on a Mac.Can you mine Bitcoin or other crypto on a MacBook or Mac mini? The honest math for Apple Silicon, what still works, and how Macs earn by running AI instead.Read the guideEarn with your Mac.Can a MacBook or Mac mini earn money while you're not using it? Every option compared honestly: bandwidth sharing, mining, renting compute and running AI with MLX.Read the guideSell your computing power.How to rent out your computer's spare power for AI: how compute marketplaces work, why most skip Macs, and how Apple Silicon Macs earn by running AI on MLX Network.Read the guideHow much power does a Mac use?Apple's idle and maximum power figures for every Apple Silicon Mac mini and Mac Studio, what running one all day costs in electricity, and why Macs are efficient for AI.Read the guide
Run AI on Apple Silicon
DeepSeek V4.1 Flash 1017.DeepSeek-V4.1-Flash-1017 explained: what changed on 17 October, benchmarks against Opus 5 and GPT-5.6 Sol, parameters, memory needs, API price and how to run it.Read the guideRun DeepSeek V4.1 Flash on a Mac.How to run DeepSeek V4.1 Flash (and 1017) locally on a Mac: how much RAM each MLX and GGUF build needs, which Mac Studio holds it, real tokens per second and commands.Read the guideRun an LLM on your Mac.Run large language models on a MacBook, Mac mini or Mac Studio, privately and offline. Step-by-step with Apple's MLX, Ollama and LM Studio, plus what fits in your Mac's memory.Read the guideDownload and run LLMs on your Mac.Where to download LLMs for a Mac, which size and quantization fit your memory, disk space, gated models, and how to run them with MLX, LM Studio and Ollama.Read the guideThe best Mac for local LLMs.Which Mac should you buy to run LLMs locally? Memory decides what fits and bandwidth decides speed. Every Apple Silicon chip compared, from MacBook Air to Mac Studio M5 Ultra.Read the guideMac AI clusters.How to build an AI cluster from Mac minis or Mac Studios: RDMA over Thunderbolt 5, MLX distributed and exo, real speedups, and why a network of Macs goes further.Read the guideMLX vs Ollama vs llama.cpp.Apple's MLX, Ollama and llama.cpp compared for running LLMs on Apple Silicon: speed, model formats, ease of use and when to pick each. Updated for Ollama's MLX preview.Read the guideThe best apps to run LLMs on a Mac.MLX Harness, LM Studio, Ollama, Jan, llama.cpp and mlx-lm compared for running local LLMs on Apple Silicon: open source or not, MLX or GGUF, app or command line, and local API.Read the guideCan my Mac run Perplexity Computer locally?Perplexity Computer now runs fully on Apple silicon Macs, with 36 GB of memory or more recommended. Which Macs have it, and what 24 GB and 32 GB Macs can still do.Read the guide
MLX Network
What is DePIN?DePIN means decentralized physical infrastructure networks: people supply hardware like storage, wireless or compute and earn tokens. How it works, the risks, and AI compute on Macs.Read the guideMLX Network and Apple's MLX.MLX is Apple's open-source machine learning framework. MLX Network (mlx.app) is an independent compute network that runs on it. What each one is, and how they relate.Read the guideIs MLX safe on my Mac?What MLX Node does on your Mac: a sandboxed, notarized app that runs AI jobs within the limits you set. What it can and can't access, the data it sends, and the risks.Read the guideHow the MLX wallet works.How the MLX wallet turns a passkey into a signing key, what the MLX ledger makes public, how balances, locks and withdrawals work, and who controls what.Read the guideApple's Minions, explained.Apple researchers pooled idle Apple silicon Macs into a virtual GPU cloud for ML inference. What the Minions paper says, what it doesn't, and how MLX Network differs.Read the guide
Apple Silicon chips for AI
Memory, bandwidth and which models fit, for every chip from M1 to M6.
M116 GB · 68 GB/sM1 Pro32 GB · 200 GB/sM1 Max64 GB · 400 GB/sM1 Ultra128 GB · 800 GB/sM224 GB · 100 GB/sM2 Pro32 GB · 200 GB/sM2 Max96 GB · 400 GB/sM2 Ultra192 GB · 800 GB/sM324 GB · 100 GB/sM3 Pro36 GB · 150 GB/sM3 Max128 GB · 400 GB/sM3 Ultra512 GB · 819 GB/sM432 GB · 120 GB/sM4 Pro64 GB · 273 GB/sM4 Max128 GB · 546 GB/sM532 GB · 153 GB/sM5 Pro64 GB · 307 GB/sM5 Max128 GB · 614 GB/sM5 Ultra512 GB · 1.2 TB/sM632 GB · 170 GB/s