noni vs Snippet Keyboard

noni is a team of small AI models that live on your iPhone. Instead of one giant model in the cloud, noni orchestrates several small open-weight language models locally: a tiny router reads each request and hands it to the right specialist - general chat, coding, or writing. Nothing you type ever leaves your phone. PRIVATE BY ARCHITECTURE • zero data collection - no account, no analytics, no tracking • conversations are stored only on your device • the network is used for one thing: downloading model weights from Hugging Face • after a model is downloaded, it works in airplane mode A TEAM, NOT A SINGLE MODEL • auto - a 0.6B router classifies each request and picks the specialist • solo - pin any downloaded model and talk to it directly • relay - pipelines like draft → polish, one model refining another's work • council - two models answer, a third merges the best of both BUILT FOR IPHONE • Apple's MLX framework with 4-bit quantized models and streaming replies • markdown rendering with copyable code cards • background, resumable model downloads • automatic conversation titles, edit & resend, regenerate • a strict black-and-white design: no clutter, no color, no distractions MODELS & SIZES (download only what you need) • qwen3 0.6b - router and quick chat, ~350 MB • llama 3.2 1b - everyday general model, ~710 MB • gemma 3 1b - rewriting and summarizing, ~770 MB • qwen2.5 coder 1.5b - writes and explains code, ~880 MB • qwen3 1.7b - stronger generalist for recent iPhones, ~980 MB • llama 3.2 3b - the most capable, for high-memory iPhones, ~1.8 GB The starter pack (router + general model) is about 1.1 GB. Models are free, open-weight, and hosted on Hugging Face. HONEST EXPECTATIONS Small local models are fast, private, and surprisingly capable for everyday questions, quick code snippets, and rewrites - but they are not cloud giants. Expect roughly 10-30 tokens per second on recent iPhones, and occasional mistakes. That is the trade for total privacy, zero cost, and offline use. Requires an iPhone with iOS 17 or later. On older or lower-memory devices, stick to the smaller models; the library labels which models want a high-memory iPhone. Built with Llama. Qwen models are Apache-2.0 by Alibaba Cloud; Gemma is provided under Google's Gemma Terms of Use; inference runs on Apple's open-source MLX.

Snippet Keyboard does exactly one job: it puts your saved phrases one tap away, in every app. Switch to it with the globe key when you need it, tap a bubble, and your full snippet is inserted — greetings, work replies, addresses, emails, anything you type over and over. Then switch right back to your normal keyboard. WHY IT'S DIFFERENT • No typing engine, no autocorrect, no bloat — it's a snippet panel, not a keyboard replacement • Tiny and fast: inserts are instant • Organize snippets into categories with emoji labels • Filter bubbles narrow a category in one tap: A+B needs both, A,B needs either • Multi-line snippets, and long-press any bubble to preview the full text • Undo takes back the last insert; the Clear key wipes what you were typing, and Undo brings it back • Keyboard size: Compact, Standard or Tall • Starter packs: ready-made customer-support replies in English, Chinese, French, Spanish and Vietnamese • Import/export your library as a simple YAML text file — the same file works on iOS and Android • Dark and light mode, iPhone and iPad • Available in 15 languages NEW: POP-UP BUBBLES Press and hold a pop-up bubble, slide to a snippet, let go — it's inserted. Snippets inside a pop-up are hidden from the main keyboard, so even a big library sits behind a few fixed buttons that never move. Filters still work exactly as before. DYNAMIC SNIPPETS Create a snippet from any https:// URL you choose — tapping it fetches and inserts live content (your public IP, a status line, anything your server returns). • Extraction rules pick out just the value you need from a JSON or HTML reply • Add text before and after the reply, so a live value lands inside a full sentence • Optionally send the text you're typing to your URL and replace it with the reply — handy for rewriting or translating a sentence. It's off by default and set per snippet, under Advanced; Undo puts your text back PRIVACY FIRST • No analytics, no tracking, no ads, no accounts • Your snippets stay on your device • The network is used ONLY when you tap a dynamic https:// snippet you created yourself • No typing engine: the keyboard doesn't store what you type, and only sends it for a dynamic snippet you've set to do so • Full Access is optional — it's needed only for dynamic snippets. Static snippets work fully without it PLANS • Free: 20 inserts a day, unlimited snippets • Pro: 100 inserts a day — one-time purchase, no subscription • Unlimited: no daily limit — auto-renewing subscription, monthly or yearly Bought Pro before these plans existed? You keep unlimited inserts. Prices are shown in the app in your local currency. Payment is charged to your Apple ID account at confirmation of purchase. The Unlimited subscription renews automatically unless cancelled at least 24 hours before the end of the current period; manage or cancel it in your App Store account settings. Terms of Use (EULA): https://www.apple.com/legal/internet-services/itunes/dev/stdeula/ Privacy Policy: https://trinh.uk/snippetkeyboard/privacy/