# MLX

> MLX Network is a community building the largest Apple Silicon compute network, live on mainnet since 2026-10-18. MLX Node, a Mac menu bar app, runs AI work on Apple Silicon Macs and mines MLX tokens, and the owner controls when and how much each Mac works (MLX, the companion app for iPhone and iPad, App Store name MLX.app, controls them remotely). MLX Harness, a Mac app for running AI models locally, carries MLX Node inside. A Mac running MLX Node is a node of the network; without a dedicated seat it runs on a free seat. A dedicated seat (formerly called a node), matched to the Mac's chip, works like a stake: it reserves the Mac's place on the network and sets how fast it mines (it pays nothing up front since 2026-10-20); sending paid AI jobs to Macs with dedicated seats first is planned. Every block, transaction and seat is public and verifiable at explorer.mlx.app. MLX is not affiliated with Apple Inc.

Key facts (from the live protocol code):
- Total supply: 10,000,000,000 MLX, fixed at genesis.
- Unit: $100. The network price follows a halving curve: what a unit buys at the curve price halves every 200,000 units, so the price doubles. Spot buys and sells are filled on this curve. Dedicated seats move the curve but pay nothing up front: they mine.
- Dedicated seat tiers: two starter seats any Apple silicon Mac runs in full, then one per Mac chip class (same $100 per unit throughout; Latest editions are for Apple's newest chips, M6, M5 Pro, M5 Max, M5 Ultra: 1.5× the price and the weight):
- Nano (starter seat: any Mac with Apple silicon, at full weight): $50, 0.5 units, mines up to 4 MLX a day, mined MLX locked 20 days. No Latest edition.
- Lite (starter seat: any Mac with Apple silicon, at full weight): $100, 1 unit, mines up to 8 MLX a day, mined MLX locked 14 days. No Latest edition.
- Core (Macs with an M-series chip): $250, 2.5 units, mines up to 20 MLX a day, mined MLX locked 10 days. Core Latest: $375, 3.75 units, up to 30 MLX a day.
- Pro (Macs with a Pro or Max chip): $1,000, 10 units, mines up to 80 MLX a day, mined MLX locked 7 days. Pro Latest: $1,500, 15 units, up to 120 MLX a day.
- Ultra (Macs with an Ultra chip): $4,000, 40 units, mines up to 320 MLX a day, mined MLX locked 3 days. Ultra Latest: $6,000, 60 units, up to 480 MLX a day.
- Allocation:
- Seat reserve: 30% (rewards.mlx)
- Compute rewards: 35% (compute.mlx)
- Community and referrals: 10% (community.mlx)
- Treasury: 15% (treasury.mlx)
- Contributors: 10% (team.mlx)
- Compute rewards: since 2026-10-17, Macs running MLX Node earn MLX hourly from the compute pool, by availability, verified work and agreement with other Macs, weighted by seat units: each dedicated seat runs on one linked Mac and earns at the smaller of the seat's class and the Mac's (starter seats earn in full on any Mac); a wallet without a dedicated seat runs on a free seat at 0.125 units and is throttled: short AI jobs on a random heartbeat (a 1–9 second wait between jobs); dedicated seats get full jobs back to back, a steady flow. Capped at 8 MLX per unit per day. Mined MLX unlocks 30 days after the day it is earned on a free seat, or after the lock-in of the wallet's shortest-locked dedicated seat (3 to 20 days); USDC paid for jobs is never locked.
- Mainnet: live since 2026-10-18. Mined MLX locks count from the day it is earned. Still to come: audits and slashing, paid jobs from clients (paid in USDC, never locked, sent to Macs with dedicated seats first), independent routers.
- MLX for iPhone and iPad (App Store name MLX.app): the free companion to MLX Node. See the Macs linked to your wallet and what they mined, pause or resume them, set their limits, and get a notification when a Mac stops. It has no wallet features yet; sending and receiving come in a later version.
- The network dollar is USDC; withdrawals are paid in USDC on Solana.
- Contact: info@mlx.app (general), support@mlx.app (wallet, seats, payments, MLX Node, MLX Harness and MLX.app), contact@mlx.app (business, legal, security). Operator: MLX Foundation, Zug, Switzerland.
- Languages: English, Chinese (Simplified), Chinese (Traditional), Hindi, Spanish, Arabic, Bengali, Portuguese, Russian, Japanese, German, French, Urdu, Indonesian, Turkish, Vietnamese, Korean, Italian, Persian, Thai, Polish, Ukrainian, Dutch, Malay, Filipino, Swahili, Tamil, Telugu, Marathi, Gujarati.

## Start here
- [llms-full.txt](https://mlx.app/llms-full.txt): this summary plus every guide in full, the seat and mining rules, the Mac and model tables, and the open data, in one plain-text file
- [Home](https://mlx.app/): what MLX is, MLX Node, dedicated seats and the token
- [Download MLX Node](https://mlx.app/download): Apple Silicon Macs (M1 or later), plus MLX Harness and MLX.app for iPhone and iPad
- [Dedicated seats](https://mlx.app/nodes): Nano, Lite, Core, Pro and Ultra seats, prices, lock-ins and what a seat does
- [Rewards](https://mlx.app/rewards): how seats mine, the most each seat mines an hour and a day, and the locks on mined MLX
- [Token](https://mlx.app/token): live MLX price, supply, holders and the curve
- [Wallet](https://wallet.mlx.app/): passkey wallet to deposit, buy dedicated seats, buy or sell MLX

## Guides
- [How to mine MLX on your Mac with MLX Node, step by step](https://mlx.app/learn/start-earning-mlx-on-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.
- [Create an MLX wallet: passkey, recovery phrase and linking a Mac](https://mlx.app/learn/create-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.
- [How to use MLX Harness: run AI models locally on your Mac](https://mlx.app/learn/how-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.
- [How to mine crypto on a Mac (M1 to M5) in 2026](https://mlx.app/learn/mine-crypto-on-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.
- [How to make money with your Mac's spare power (2026)](https://mlx.app/learn/make-money-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.
- [Sell or rent out your computing power for AI (2026)](https://mlx.app/learn/sell-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.
- [How much power does a Mac use? Mac mini and Mac Studio watts](https://mlx.app/learn/mac-power-consumption): 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.
- [DeepSeek V4.1 Flash 1017: benchmarks, size, price, how to run](https://mlx.app/learn/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.
- [Run DeepSeek V4.1 Flash on a Mac: memory, speed, which Mac](https://mlx.app/learn/run-deepseek-v4-1-flash-on-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.
- [How to run an LLM locally on your Mac (MLX, Ollama, LM Studio)](https://mlx.app/learn/run-llm-on-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.
- [Download LLMs and run them locally on your Mac: a practical guide](https://mlx.app/learn/download-and-run-llms-on-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.
- [Best Mac for local LLMs in 2026: memory, bandwidth, chips](https://mlx.app/learn/best-mac-for-local-llm): 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.
- [Mac AI clusters: Mac mini and Mac Studio over Thunderbolt 5](https://mlx.app/learn/mac-ai-cluster): 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.
- [MLX vs Ollama vs llama.cpp on a Mac: which to use](https://mlx.app/learn/mlx-vs-ollama): 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.
- [What is DePIN? Decentralized AI compute, explained](https://mlx.app/learn/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.
- [MLX Network vs Apple's MLX framework: what's the difference](https://mlx.app/learn/mlx-network-vs-apple-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.
- [Is MLX Node safe? What it runs on your Mac and what it can see](https://mlx.app/learn/is-mlx-safe): 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.
- [How the MLX wallet works: passkeys, keys, balances and locks](https://mlx.app/learn/how-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.
- [Best apps to run LLMs on a Mac in 2026, compared](https://mlx.app/learn/best-apps-to-run-llm-on-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.
- [Can my Mac run Perplexity Computer locally? Memory and Macs](https://mlx.app/learn/run-perplexity-computer-locally-on-mac): 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.
- [Apple's Minions: a GPU cloud from idle Macs, explained](https://mlx.app/learn/apple-minions-idle-mac-gpu-cloud): 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.
- [macOS fm command: Apple's free local LLM in Terminal](https://mlx.app/learn/macos-fm-command-free-local-llm): macOS 27 comes with fm, a Terminal tool for Apple's on-device Foundation Model. Its commands, what you need, its limits, and when an open model on your Mac does more.
- [MLX World](https://world.mlx.app/): every Mac on the network on a live map
- [Source code on GitHub](https://github.com/MLXapp): MLX Node for Mac and MLX.app for iPhone, Apache-2.0
- [MLX Harness](https://harness.mlx.app/): a free, open-source Mac app for running AI models locally (chat, agents, images, local OpenAI- and Anthropic-compatible API), built on vMLX by JANGQ AI; it carries MLX Node inside
- [Download MLX Harness](https://mlx.app/api/download/harness): the latest signed, notarized release (DMG, Apple Silicon, macOS 14.5 or later); releases and source at https://github.com/MLXapp/harness

## Can a Mac run it? (local AI on Apple Silicon)
- [Compare](https://mlx.app/compare): pick any Mac or GPU and see which open models fit its memory and how fast it writes
- [Every Mac](https://mlx.app/mac): each Apple Silicon chip and memory size (M1 to M6), with every model it runs
- [Every model](https://mlx.app/run): the memory each open model needs and the smallest Mac that runs it
- By Mac model: [Mac mini M6](https://mlx.app/mac/mac-mini-m6), [Mac mini M5 Pro](https://mlx.app/mac/mac-mini-m5-pro), [Mac mini M4](https://mlx.app/mac/mac-mini-m4), [Mac mini M4 Pro](https://mlx.app/mac/mac-mini-m4-pro), [Mac mini M2](https://mlx.app/mac/mac-mini-m2), [Mac mini M2 Pro](https://mlx.app/mac/mac-mini-m2-pro), [Mac mini M1](https://mlx.app/mac/mac-mini-m1), [MacBook Air M5](https://mlx.app/mac/macbook-air-m5), [MacBook Air M4](https://mlx.app/mac/macbook-air-m4), [MacBook Air M3](https://mlx.app/mac/macbook-air-m3), [MacBook Air M2](https://mlx.app/mac/macbook-air-m2), [MacBook Air M1](https://mlx.app/mac/macbook-air-m1), [MacBook Pro M5](https://mlx.app/mac/macbook-pro-m5), [MacBook Pro M5 Pro](https://mlx.app/mac/macbook-pro-m5-pro), [MacBook Pro M5 Max](https://mlx.app/mac/macbook-pro-m5-max), [MacBook Pro M4](https://mlx.app/mac/macbook-pro-m4), [MacBook Pro M4 Pro](https://mlx.app/mac/macbook-pro-m4-pro), [MacBook Pro M4 Max](https://mlx.app/mac/macbook-pro-m4-max), [MacBook Pro M3](https://mlx.app/mac/macbook-pro-m3), [MacBook Pro M3 Pro](https://mlx.app/mac/macbook-pro-m3-pro), [MacBook Pro M3 Max](https://mlx.app/mac/macbook-pro-m3-max), [MacBook Pro M2](https://mlx.app/mac/macbook-pro-m2), [MacBook Pro M2 Pro](https://mlx.app/mac/macbook-pro-m2-pro), [MacBook Pro M2 Max](https://mlx.app/mac/macbook-pro-m2-max), [MacBook Pro M1](https://mlx.app/mac/macbook-pro-m1), [MacBook Pro M1 Pro](https://mlx.app/mac/macbook-pro-m1-pro), [MacBook Pro M1 Max](https://mlx.app/mac/macbook-pro-m1-max), [iMac M4](https://mlx.app/mac/imac-m4), [iMac M3](https://mlx.app/mac/imac-m3), [iMac M1](https://mlx.app/mac/imac-m1), [Mac Studio M5 Max](https://mlx.app/mac/mac-studio-m5-max), [Mac Studio M5 Ultra](https://mlx.app/mac/mac-studio-m5-ultra), [Mac Studio M4 Max](https://mlx.app/mac/mac-studio-m4-max), [Mac Studio M3 Ultra](https://mlx.app/mac/mac-studio-m3-ultra), [Mac Studio M2 Max](https://mlx.app/mac/mac-studio-m2-max), [Mac Studio M2 Ultra](https://mlx.app/mac/mac-studio-m2-ultra), [Mac Studio M1 Max](https://mlx.app/mac/mac-studio-m1-max), [Mac Studio M1 Ultra](https://mlx.app/mac/mac-studio-m1-ultra), [Mac Pro M2 Ultra](https://mlx.app/mac/mac-pro-m2-ultra)
- [Every Mac ranked for local AI](https://mlx.app/mac/ranking)
- Best LLMs by memory: [8 GB](https://mlx.app/mac/8gb), [16 GB](https://mlx.app/mac/16gb), [18 GB](https://mlx.app/mac/18gb), [24 GB](https://mlx.app/mac/24gb), [32 GB](https://mlx.app/mac/32gb), [36 GB](https://mlx.app/mac/36gb), [48 GB](https://mlx.app/mac/48gb), [64 GB](https://mlx.app/mac/64gb), [96 GB](https://mlx.app/mac/96gb), [128 GB](https://mlx.app/mac/128gb), [192 GB](https://mlx.app/mac/192gb), [256 GB](https://mlx.app/mac/256gb), [512 GB](https://mlx.app/mac/512gb)
- Chip vs chip for local AI: [M1 vs M1 Pro](https://mlx.app/mac/m1-vs-m1-pro), [M1 Pro vs M1 Max](https://mlx.app/mac/m1-pro-vs-m1-max), [M1 Max vs M1 Ultra](https://mlx.app/mac/m1-max-vs-m1-ultra), [M1 vs M2](https://mlx.app/mac/m1-vs-m2), [M1 Pro vs M2 Pro](https://mlx.app/mac/m1-pro-vs-m2-pro), [M2 vs M2 Pro](https://mlx.app/mac/m2-vs-m2-pro), [M1 Max vs M2 Max](https://mlx.app/mac/m1-max-vs-m2-max), [M2 Pro vs M2 Max](https://mlx.app/mac/m2-pro-vs-m2-max), [M1 Ultra vs M2 Ultra](https://mlx.app/mac/m1-ultra-vs-m2-ultra), [M2 Max vs M2 Ultra](https://mlx.app/mac/m2-max-vs-m2-ultra), [M2 vs M3](https://mlx.app/mac/m2-vs-m3), [M2 Pro vs M3 Pro](https://mlx.app/mac/m2-pro-vs-m3-pro), [M3 vs M3 Pro](https://mlx.app/mac/m3-vs-m3-pro), [M2 Max vs M3 Max](https://mlx.app/mac/m2-max-vs-m3-max), [M3 Pro vs M3 Max](https://mlx.app/mac/m3-pro-vs-m3-max), [M2 Ultra vs M3 Ultra](https://mlx.app/mac/m2-ultra-vs-m3-ultra), [M3 Max vs M3 Ultra](https://mlx.app/mac/m3-max-vs-m3-ultra), [M1 vs M4](https://mlx.app/mac/m1-vs-m4), [M2 vs M4](https://mlx.app/mac/m2-vs-m4), [M3 vs M4](https://mlx.app/mac/m3-vs-m4), [M1 Pro vs M4 Pro](https://mlx.app/mac/m1-pro-vs-m4-pro), [M3 Pro vs M4 Pro](https://mlx.app/mac/m3-pro-vs-m4-pro), [M4 vs M4 Pro](https://mlx.app/mac/m4-vs-m4-pro), [M1 Max vs M4 Max](https://mlx.app/mac/m1-max-vs-m4-max), [M2 Max vs M4 Max](https://mlx.app/mac/m2-max-vs-m4-max), [M2 Ultra vs M4 Max](https://mlx.app/mac/m2-ultra-vs-m4-max), [M3 Max vs M4 Max](https://mlx.app/mac/m3-max-vs-m4-max), [M3 Ultra vs M4 Max](https://mlx.app/mac/m3-ultra-vs-m4-max), [M4 Pro vs M4 Max](https://mlx.app/mac/m4-pro-vs-m4-max), [M4 vs M5](https://mlx.app/mac/m4-vs-m5), [M4 Pro vs M5 Pro](https://mlx.app/mac/m4-pro-vs-m5-pro), [M5 vs M5 Pro](https://mlx.app/mac/m5-vs-m5-pro), [M1 Max vs M5 Max](https://mlx.app/mac/m1-max-vs-m5-max), [M3 Ultra vs M5 Max](https://mlx.app/mac/m3-ultra-vs-m5-max), [M4 Pro vs M5 Max](https://mlx.app/mac/m4-pro-vs-m5-max), [M4 Max vs M5 Max](https://mlx.app/mac/m4-max-vs-m5-max), [M5 Pro vs M5 Max](https://mlx.app/mac/m5-pro-vs-m5-max), [M3 Ultra vs M5 Ultra](https://mlx.app/mac/m3-ultra-vs-m5-ultra), [M4 Max vs M5 Ultra](https://mlx.app/mac/m4-max-vs-m5-ultra), [M5 Max vs M5 Ultra](https://mlx.app/mac/m5-max-vs-m5-ultra), [M5 vs M6](https://mlx.app/mac/m5-vs-m6)
- Mac vs PC for local AI (DGX Spark, Ryzen AI Max, RTX cards; memory, bandwidth, llama.cpp measurements): [M4 Max vs DGX Spark](https://mlx.app/mac/m4-max-vs-dgx-spark), [M5 Max vs DGX Spark](https://mlx.app/mac/m5-max-vs-dgx-spark), [M3 Ultra vs DGX Spark](https://mlx.app/mac/m3-ultra-vs-dgx-spark), [M5 Ultra vs DGX Spark](https://mlx.app/mac/m5-ultra-vs-dgx-spark), [M4 Pro vs Ryzen AI Max+ 395](https://mlx.app/mac/m4-pro-vs-ryzen-ai-max-395), [M4 Max vs Ryzen AI Max+ 395](https://mlx.app/mac/m4-max-vs-ryzen-ai-max-395), [M5 Max vs Ryzen AI Max+ 395](https://mlx.app/mac/m5-max-vs-ryzen-ai-max-395), [M5 Max vs Ryzen AI Max+ PRO 495](https://mlx.app/mac/m5-max-vs-ryzen-ai-max-495), [M5 Max vs RTX 5090](https://mlx.app/mac/m5-max-vs-rtx-5090), [M5 Ultra vs RTX PRO 6000](https://mlx.app/mac/m5-ultra-vs-rtx-pro-6000)
- [Every M chip for local AI](https://mlx.app/learn/chip): one table of every Apple Silicon chip: memory, bandwidth, the biggest model it holds at 4-bit and the speed ceiling for an 8B model, from Apple's figures
- [Can a Mac run DeepSeek V4.1 Flash 1017?](https://mlx.app/run/deepseek-v4.1-flash-1017): 4-bit needs about 335 GB; smallest Mac 512 GB; up to 60–107 tokens/s (estimate) on an M5 Ultra 512 GB
- [Can a Mac run DeepSeek V4 Pro 0813?](https://mlx.app/run/deepseek-v4-pro-0813): 4-bit needs about 972 GB; no single Mac holds it
- [Can a Mac run DeepSeek V4 Flash 0731?](https://mlx.app/run/deepseek-v4-flash-0731): 4-bit needs about 173 GB; smallest Mac 256 GB; up to 74–132 tokens/s (estimate) on an M5 Ultra 256 GB
- [Can a Mac run Qwen3.8 27B?](https://mlx.app/run/qwen3.8-27b): 4-bit needs about 16.7 GB; smallest Mac 24 GB; up to 19–33 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Qwen3.8 Flash Next?](https://mlx.app/run/qwen3.8-flash-next): 4-bit needs about 109 GB; smallest Mac 192 GB; up to 110–196 tokens/s (estimate) on an M5 Ultra 256 GB
- [Can a Mac run Qwen3.8 2.4T A95B?](https://mlx.app/run/qwen3.8-2.4t-a95b): 4-bit needs about 1.5 TB; no single Mac holds it
- [Can a Mac run Qwen3.5 397B A17B?](https://mlx.app/run/qwen3.5-397b-a17b): 4-bit needs about 241 GB; smallest Mac 512 GB; up to 39–70 tokens/s (estimate) on an M5 Ultra 512 GB
- [Can a Mac run Qwen3.5 122B A10B?](https://mlx.app/run/qwen3.5-122b-a10b): 4-bit needs about 74.1 GB; smallest Mac 128 GB; up to 64–114 tokens/s (estimate) on an M2 Ultra 128 GB
- [Can a Mac run Ornith 1.5 122B?](https://mlx.app/run/ornith-1.5-122b): 4-bit needs about 74.1 GB; smallest Mac 128 GB; up to 64–114 tokens/s (estimate) on an M2 Ultra 128 GB
- [Can a Mac run Qwen3.6 35B A3B?](https://mlx.app/run/qwen3.6-35b-a3b): 4-bit needs about 21.3 GB; smallest Mac 32 GB; up to 169–300 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Qwen3.6 27B?](https://mlx.app/run/qwen3.6-27b): 4-bit needs about 16.7 GB; smallest Mac 24 GB; up to 19–33 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Qwen3.5 9B?](https://mlx.app/run/qwen3.5-9b): 4-bit needs about 6.6 GB; smallest Mac 16 GB; up to 56–100 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Qwen3.5 4B?](https://mlx.app/run/qwen3.5-4b): 4-bit needs about 3.8 GB; smallest Mac 8 GB; up to 126–223 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Qwen3.5 2B?](https://mlx.app/run/qwen3.5-2b): 4-bit needs about 2.6 GB; smallest Mac 8 GB; up to 257–457 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Qwen3.5 0.8B?](https://mlx.app/run/qwen3.5-0.8b): 4-bit needs about 2 GB; smallest Mac 8 GB; up to 600–1067 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Qwen3 Coder Next?](https://mlx.app/run/qwen3-coder-next): 4-bit needs about 48.6 GB; smallest Mac 96 GB; up to 225–400 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Qwen3 Coder 30B A3B Instruct?](https://mlx.app/run/qwen3-coder-30b-a3b): 4-bit needs about 18.7 GB; smallest Mac 32 GB; up to 154–274 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Qwen3 8B?](https://mlx.app/run/qwen3-8b): 4-bit needs about 6.1 GB; smallest Mac 16 GB; up to 62–110 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Qwen3 0.6B?](https://mlx.app/run/qwen3-0.6b): 4-bit needs about 1.8 GB; smallest Mac 8 GB; up to 900–1600 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run gpt-oss-20b?](https://mlx.app/run/gpt-oss-20b): native 4.25-bit needs about 15.3 GB; smallest Mac 24 GB; up to 284–505 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run gpt-oss-120b?](https://mlx.app/run/gpt-oss-120b): native 4.25-bit needs about 70.5 GB; smallest Mac 96 GB; up to 200–356 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Llama 3.1 8B Instruct?](https://mlx.app/run/llama-3.1-8b): 4-bit needs about 6 GB; smallest Mac 8 GB; up to 64–113 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Llama 3.3 70B Instruct?](https://mlx.app/run/llama-3.3-70b): 4-bit needs about 42.6 GB; smallest Mac 64 GB; up to 14–24 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Llama 4 Scout 17B-16E Instruct?](https://mlx.app/run/llama-4-scout): 4-bit needs about 66.2 GB; smallest Mac 96 GB; up to 56–100 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Llama 4 Maverick 17B-128E Instruct?](https://mlx.app/run/llama-4-maverick): 4-bit needs about 243 GB; smallest Mac 512 GB; up to 39–70 tokens/s (estimate) on an M5 Ultra 512 GB
- [Can a Mac run Llama 3.2 1B Instruct?](https://mlx.app/run/llama-3.2-1b): 4-bit needs about 2.2 GB; smallest Mac 8 GB; up to 415–738 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Llama 3.2 3B Instruct?](https://mlx.app/run/llama-3.2-3b): 4-bit needs about 3.3 GB; smallest Mac 8 GB; up to 159–282 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Muse Spark Open?](https://mlx.app/run/muse-spark-open): 4-bit needs about 496 GB; smallest Mac 512 GB; up to 41–73 tokens/s (estimate) on an M5 Ultra 512 GB
- [Can a Mac run Muse Glimmer 30B?](https://mlx.app/run/muse-glimmer-30b): 4-bit needs about 18.2 GB; smallest Mac 32 GB; up to 17–30 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Gemma 4 31B?](https://mlx.app/run/gemma-4-31b): 4-bit needs about 18.8 GB; smallest Mac 32 GB; up to 17–29 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Gemma 4 26B A4B?](https://mlx.app/run/gemma-4-26b-a4b): 4-bit needs about 15.7 GB; smallest Mac 24 GB; up to 135–240 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Gemma 4 12B Unified?](https://mlx.app/run/gemma-4-12b): 4-bit needs about 8.2 GB; smallest Mac 16 GB; up to 43–76 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Gemma 4 E4B?](https://mlx.app/run/gemma-4-e4b): 4-bit needs about 6 GB; smallest Mac 8 GB; up to 113–200 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Gemma 4 E2B?](https://mlx.app/run/gemma-4-e2b): 4-bit needs about 4.4 GB; smallest Mac 8 GB; up to 225–400 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Mistral Small 4 (119B)?](https://mlx.app/run/mistral-small-4): 4-bit needs about 72.3 GB; smallest Mac 128 GB; up to 97–173 tokens/s (estimate) on an M2 Ultra 128 GB
- [Can a Mac run Mistral Medium 3.5 (128B)?](https://mlx.app/run/mistral-medium-3.5): 4-bit needs about 77.8 GB; smallest Mac 128 GB; up to 5–9 tokens/s (estimate) on an M2 Ultra 128 GB
- [Can a Mac run Mistral Large 3 (675B)?](https://mlx.app/run/mistral-large-3): 4-bit needs about 410 GB; smallest Mac 512 GB; up to 30–54 tokens/s (estimate) on an M5 Ultra 512 GB
- [Can a Mac run Devstral Small 2 (24B)?](https://mlx.app/run/devstral-small-2): 4-bit needs about 15 GB; smallest Mac 24 GB; up to 21–38 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Devstral 2 (123B)?](https://mlx.app/run/devstral-2-123b): 4-bit needs about 74.7 GB; smallest Mac 128 GB; up to 5–9 tokens/s (estimate) on an M2 Ultra 128 GB
- [Can a Mac run Magistral Small 1.2 (2509)?](https://mlx.app/run/magistral-small-2509): 4-bit needs about 15 GB; smallest Mac 24 GB; up to 21–38 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Ministral 3 8B?](https://mlx.app/run/ministral-3-8b): 4-bit needs about 6.5 GB; smallest Mac 16 GB; up to 57–101 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Mistral Small 3.2 (24B)?](https://mlx.app/run/mistral-small-3.2): 4-bit needs about 15 GB; smallest Mac 24 GB; up to 21–38 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Phi-4 (14B)?](https://mlx.app/run/phi-4): 4-bit needs about 9.4 GB; smallest Mac 16 GB; up to 36–64 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Phi-4 mini instruct?](https://mlx.app/run/phi-4-mini): 4-bit needs about 3.6 GB; smallest Mac 8 GB; up to 135–240 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Phi-4 Reasoning Vision 15B?](https://mlx.app/run/phi-4-reasoning-vision-15b): 4-bit needs about 9.9 GB; smallest Mac 16 GB; up to 34–60 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Kimi K3?](https://mlx.app/run/kimi-k3): native 4.25-bit needs about 1.7 TB; no single Mac holds it
- [Can a Mac run Kimi K2.6?](https://mlx.app/run/kimi-k2.6): native 4-bit needs about 643 GB; smallest Mac 512 GB; up to 54–96 tokens/s (estimate) on an M5 Ultra 512 GB
- [Can a Mac run Kimi K2.7 Code?](https://mlx.app/run/kimi-k2.7-code): native 4-bit needs about 643 GB; smallest Mac 512 GB; up to 54–96 tokens/s (estimate) on an M5 Ultra 512 GB
- [Can a Mac run GLM-5.3?](https://mlx.app/run/glm-5.3): 4-bit needs about 452 GB; smallest Mac 512 GB; up to 31–55 tokens/s (estimate) on an M5 Ultra 512 GB
- [Can a Mac run GLM-5.3 Flash?](https://mlx.app/run/glm-5.3-flash): 4-bit needs about 194 GB; smallest Mac 512 GB; up to 28–50 tokens/s (estimate) on an M5 Ultra 512 GB
- [Can a Mac run GLM-4.7 Flash?](https://mlx.app/run/glm-4.7-flash): 4-bit needs about 18.4 GB; smallest Mac 32 GB; up to 169–300 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run GLM-4.5 Air?](https://mlx.app/run/glm-4.5-air): 4-bit needs about 64.4 GB; smallest Mac 96 GB; up to 79–141 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run MiniMax M3?](https://mlx.app/run/minimax-m3): 4-bit needs about 260 GB; smallest Mac 512 GB; up to 29–51 tokens/s (estimate) on an M5 Ultra 512 GB
- [Can a Mac run MiniMax M2.7?](https://mlx.app/run/minimax-m2.7): 4-bit needs about 140 GB; smallest Mac 192 GB; up to 96–171 tokens/s (estimate) on an M5 Ultra 256 GB
- [Can a Mac run Nemotron 3 Nano 30B A3B?](https://mlx.app/run/nemotron-3-nano-30b-a3b): 4-bit needs about 18.4 GB; smallest Mac 32 GB; up to 146–259 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Nemotron 3.5 Lightning 30B A3B?](https://mlx.app/run/nemotron-3.5-lightning-30b-a3b): 4-bit needs about 18.4 GB; smallest Mac 32 GB; up to 169–300 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Nemotron 3 Super 120B A12B?](https://mlx.app/run/nemotron-3-super-120b-a12b): 4-bit needs about 72.9 GB; smallest Mac 128 GB; up to 53–94 tokens/s (estimate) on an M2 Ultra 128 GB
- [Can a Mac run Nemotron 3.5 Bolt 74B A9B?](https://mlx.app/run/nemotron-3.5-bolt-74b-a9b): 4-bit needs about 44.9 GB; smallest Mac 64 GB; up to 74–132 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Nemotron 3 Ultra 550B A55B?](https://mlx.app/run/nemotron-3-ultra-550b-a55b): 4-bit needs about 334 GB; smallest Mac 512 GB; up to 17–31 tokens/s (estimate) on an M5 Ultra 512 GB
- [Can a Mac run Nemotron 3 Nano 4B?](https://mlx.app/run/nemotron-3-nano-4b): 4-bit needs about 3.7 GB; smallest Mac 8 GB; up to 129–229 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Granite 4.2 8B?](https://mlx.app/run/granite-4.2-8b): 4-bit needs about 6 GB; smallest Mac 8 GB; up to 64–113 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Granite 4.2 3B?](https://mlx.app/run/granite-4.2-3b): 4-bit needs about 3.2 GB; smallest Mac 8 GB; up to 169–300 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Granite 4.2 30B?](https://mlx.app/run/granite-4.2-30b): 4-bit needs about 18.4 GB; smallest Mac 32 GB; up to 17–30 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run SmolLM3 3B?](https://mlx.app/run/smollm3-3b): 4-bit needs about 3.2 GB; smallest Mac 8 GB; up to 169–300 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run LFM2.5 24B A2B?](https://mlx.app/run/lfm2.5-24b-a2b): 4-bit needs about 15 GB; smallest Mac 24 GB; up to 257–457 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run LFM2.5 2.6B?](https://mlx.app/run/lfm2.5-2.6b): 4-bit needs about 3 GB; smallest Mac 8 GB; up to 186–331 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run MiniCPM5 2B?](https://mlx.app/run/minicpm5-2b): 4-bit needs about 2.9 GB; smallest Mac 8 GB; up to 200–356 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Hy3?](https://mlx.app/run/hy3): 4-bit needs about 179 GB; smallest Mac 256 GB; up to 46–81 tokens/s (estimate) on an M5 Ultra 256 GB
- [Can a Mac run MiMo V2.6 Flash?](https://mlx.app/run/mimo-v2.6-flash): native 4.48-bit needs about 187 GB; smallest Mac 256 GB; up to 64–114 tokens/s (estimate) on an M5 Ultra 256 GB
- [Can a Mac run MiMo V2.6 Pro?](https://mlx.app/run/mimo-v2.6-pro): native 4.44-bit needs about 611 GB; smallest Mac 512 GB; up to 41–73 tokens/s (estimate) on an M5 Ultra 512 GB
- [Can a Mac run Raon-1 mini Preview?](https://mlx.app/run/raon-1-mini-preview): 4-bit needs about 17.7 GB; smallest Mac 24 GB; up to 117–209 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Recursive Flint?](https://mlx.app/run/flint): 4-bit needs about 24.2 GB; smallest Mac 36 GB; up to 200–356 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Hy-Memory-30B-A3B?](https://mlx.app/run/hy-memory-30b-a3b): 4-bit needs about 18.4 GB; smallest Mac 32 GB; up to 159–282 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Ling 3.1 Flash?](https://mlx.app/run/ling-3.1-flash): 4-bit needs about 340 GB; smallest Mac 512 GB; up to 38–68 tokens/s (estimate) on an M5 Ultra 512 GB
- [Can a Mac run Nemotron-Labs Dory 1.0 4B?](https://mlx.app/run/nemotron-labs-dory-1.0-4b): 4-bit needs about 3.7 GB; smallest Mac 8 GB; up to 87–155 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Nemotron 3.5 Super VL 120B A12B?](https://mlx.app/run/nemotron-3.5-super-vl-120b-a12b): 4-bit needs about 72.9 GB; smallest Mac 128 GB; up to 53–94 tokens/s (estimate) on an M2 Ultra 128 GB
- [Can a Mac run Sage-A1.5?](https://mlx.app/run/sage-a1.5): 4-bit needs about 21.3 GB; smallest Mac 32 GB; up to 174–310 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Spark-X2.6 4B?](https://mlx.app/run/spark-x2.6-4b): 4-bit needs about 3.8 GB; smallest Mac 8 GB; up to 123–218 tokens/s (estimate) on an M5 Ultra 96 GB
- [Can a Mac run Beam 1.0?](https://mlx.app/run/beam-1.0): 4-bit needs about 304 GB; smallest Mac 512 GB; up to 42–74 tokens/s (estimate) on an M5 Ultra 512 GB
- [Can a Mac run Inkling?](https://mlx.app/run/inkling): 4-bit needs about 592 GB; smallest Mac 512 GB; up to 42–75 tokens/s (estimate) on an M5 Ultra 512 GB
- [Can a Mac run Inkling Small?](https://mlx.app/run/inkling-small): 4-bit needs about 168 GB; smallest Mac 256 GB; up to 79–141 tokens/s (estimate) on an M5 Ultra 256 GB

## Reference
- [Whitepaper](https://mlx.app/whitepaper): protocol, verification, rewards and economics, with sources
- [Explorer](https://explorer.mlx.app/): every block, transaction, account and dedicated seat
- [Open data](https://mlx.app/data): free JSON and CSV downloads (CC BY 4.0, version 2026-10-19) of every Apple Silicon Mac configuration (58), every open model (82) and the fit table of which model runs on which Mac and how fast (4,698 rows, estimates): [macs.csv](https://mlx.app/data/macs.csv), [models.csv](https://mlx.app/data/models.csv), [fit.csv](https://mlx.app/data/fit.csv), JSON next to each, [index.json](https://mlx.app/data/index.json)
- [Explorer API](https://explorer.mlx.app/api): JSON endpoints for blocks, transactions, seats and supply
- [Bench](https://mlx.app/bench): open benchmark of LLM inference on Apple Silicon, including Thunderbolt 5 pods
- [Builders](https://mlx.app/builders): dedicated seats granted for open-source MLX work
- [Embed and link](https://mlx.app/embed): the live network map as an iframe, README badges, which page to link and how to quote our data

## Policies
- [Risks](https://mlx.app/risks): read before buying; locks, price risk and operator risk
- [Terms](https://mlx.app/terms)
- [Privacy](https://mlx.app/privacy)
- [Proof of reserves](https://mlx.app/reserves)