MLXHub vs Difftray

Run AI locally. Your device. Your data. MLXHub brings open-source language models to iPhone and iPad, powered by Apple Silicon and the mlx-swift inference engine. Your conversations never leave your device. Distributed inference across your devices (Experimental) Pool memory from several Apple Silicon devices on the same Wi-Fi network to run a model that none of them could hold alone. One device hosts; the others join and each takes a slice of the model's layers — no device stores the whole thing. The host sends each device only the files its own layers need, and caches them so the next session starts faster. What to expect: every device must be on the same Wi-Fi, you approve each device once by matching a code on both screens, and MLXHub measures each device's memory before it splits anything. This is an experimental feature — distributed generation works, but a run can still stall or drop a device, and not every model architecture can be split yet. It pays off most with large models. Joining a mesh is free on any device; hosting one is part of MLXHub Plus. Chat with powerful models Download and run LLMs and vision-language models (VLMs) directly on your device. Send text messages or attach photos — the model sees and responds without touching any server. Apple Intelligence built in On supported devices (iPhone 15 Pro / 16 and later with Apple Intelligence enabled), use Apple's on-device model for instant, private responses alongside any downloaded model. Your personality, your assistant Set a global Agent Personality to define the AI's tone and style. Override it per-conversation with custom system instructions. No prompt engineering needed — just describe what you want. Browse and install models Explore a curated catalog of optimized models — from tiny 0.6B models that fit in under 1 GB to powerful 7B models for deeper reasoning. Color-coded RAM badges tell you at a glance whether a model fits your device. Search HuggingFace directly to install any compatible model. Local LAN server Turn your iPhone or iPad into a portable, chat API-compatible inference endpoint on your local network. MLXHub's optional LAN server exposes /v1/chat/completions so any app — from a Mac running OpenCode to a custom script — can use your device's models. No internet required. Auth-protected. Bonjour-discoverable. Part of MLXHub Plus. Built for Apple Silicon MLXHub uses mlx-swift, Apple's own machine-learning framework, to run models at full Metal GPU speed. Model weights are quantized (4-bit, 8-bit) for the best quality-per-GB ratio on iPhone and iPad hardware. Privacy Model inference happens on your device and never leaves it. No account. No ads. The optional LAN server only listens on your local network and is off by default. MLXHub collects a small amount of anonymous diagnostic data to find crashes and broken model loads; it is not linked to you, and you can turn it off in Settings. Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/

Difftray brings code review to your phone and tablet. Pair it with the open-source Difftray desktop app, then read git diffs, browse every changed file, and leave line-by-line comments — all over your own local network, with no cloud in between. Difftray is a companion app. It works alongside the Difftray desktop app running on your Mac. Scan a QR code once to pair, then pick up any project from the couch, a meeting room, or the other side of the office. REVIEW DIFFS ANYWHERE Read inline diffs with real syntax highlighting, sized for small screens. See additions and deletions at a glance, move between changes, and mark each file reviewed as you go. BROWSE CHANGED FILES Step through every changed file in a project and see exactly what moved, with per-file and total added/removed line counts. HAND OFF TO YOUR CODING AGENT Leave comments on the lines that need work, then export them as an agent-ready prompt. Copy it or share it straight into your AI coding agent so the fixes are queued up before you're back at your keyboard. ALL YOUR PROJECTS Every project open on your desktop is one tap away on your phone or tablet. PAIR LOCALLY, STAY PRIVATE Connect by scanning a QR code or entering a short code — no account, no sign-up. Your phone talks directly to your own computer over local Wi-Fi, or over your private Tailscale network when you're away from your desk. Pairing is end-to-end encrypted, and your code never touches a server we run. REQUIREMENTS Difftray requires the free, open-source Difftray desktop app with its companion server enabled. This mobile app is a companion to that desktop app and does not work on its own. Pair your phone, step away from your desk, and keep reviewing. Terms of Use: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/