Python IDE & Jupyter vs LemoLM

Zero-setup Python IDE that runs your code offline, an AI coding assistant, and a developer toolbox — in a first-class citizen app for iPad and iPhone. Juno is designed to cover all your Python coding needs, supporting both Python scripts (.py) and Jupyter notebooks (.ipynb) — a document format focused on applying Python to data analysis and computational science. FREE FEATURES - Navigate and manage files and folders, quickly preview documents and media - Browse and edit Jupyter notebooks in a powerful, customizable notebook editor with beautifully rendered previews — editing is free - Write and edit code sources, scripts, JSON, XML, and other text-based formats — one versatile editor for code and text alike, with syntax highlighting - Add quick access bookmarks for file system locations outside the app's sandbox, or simply open documents in place PRO FEATURES Only one thing in Juno is Pro: running code. Even that is free to try — a generous trial allowance lets you run notebooks, scripts, projects, and the REPL before you buy. After the trial, running code unlocks with a one-time Pro purchase — not a subscription. - Run Jupyter notebooks, Python scripts, and whole projects locally with the built-in Python 3.13 interpreter and a full suite of up-to-date, preinstalled scientific and data packages — entirely offline - Explore interactively in a Python REPL — open a standalone prompt, or drop into it after running a script or project to keep exploring what it defined - Search the variables, functions, and imports in your session with the Object Inspector — no need to print each one - Open any folder as a project: file tree, multiple editor tabs, run any script, with a coding assistant aware of the whole project - Keep side outputs — Preview, Browser, Console, Object Inspector — open as side-by-side tabs in an output sidebar - View local web servers and HTML your code produces in a built-in browser with developer debug tools - Long-running scripts and Jupyter sessions keep going in the background - Automate with Shortcuts and Siri: App Intents run a Python file, run Python code, or open a file — pass arguments and files, capture output, and chain actions - Leverage powerful data analysis, machine learning and developer tools: NumPy, pandas, Polars, DuckDB, Matplotlib, SciPy, Scikit-learn, OpenCV, pygame, and more - Enjoy painless package management: install any pure Python package with an intuitive package manager AI CODING ASSISTANT The assistant runs on your account or your key, not ours: sign in with your account or add your OpenAI, Anthropic, or Gemini API key, and requests go straight from your device to your provider. You control what you spend and share — Juno never takes a cut. GAMES AND EMULATORS pygame is built in: write games with touch controls, sound, and full-screen graphics, and play them on your device. Eight complete games ship as examples, alongside NES, Game Boy, and CHIP-8 emulators written in Python, each with a library of freely licensed homebrew games — play them, then open the code to see how they work. PYTHON MEETS iOS Reach native iOS APIs straight from Python with the built-in juno modules: clipboard, Keychain, device info, location, motion sensors, contacts, reminders, photos, sound, notifications, sharing, and Bluetooth. Show native alerts and pickers, present full-screen image, video, and web previews, or call into UIKit, Foundation, and any Objective-C framework via the Objective-C bridge. SCRIPTS AND NOTEBOOKS Python scripts (.py) get snappy, intelligent code completion, a console with a full terminal emulator, and a built-in media viewer for code-generated images, plots, and web apps. Jupyter notebooks (.ipynb) keep live code, markdown text, plots, images, and LaTeX equations in one file, with every output embedded right in the document — a perfect playground for data analysis and computational science.

Explore Qwen3, DeepSeek R1, Mistral, Phi-4 and other local models directly on your iPhone or iPad. On a suitable Apple silicon Mac, explore the same model catalogue plus the desktop-class OpenAI gpt-oss-20b. No account. No server. Supported downloaded models can run without an internet connection. LemoLM is a local-first playground for running, testing and comparing on-device language models, with detailed performance information for each generation. FREE, NO ACCOUNT NEEDED • Qwen3 1.7B — multilingual, with optional thinking mode • SmolLM2 1.7B — compact, for older and lower-memory devices • Apple Foundation Models — on supported devices • Mock Engine — explore the interface without downloading anything UNLOCK THE FULL MODEL PLAYGROUND One purchase, no subscription. Adds access to twelve additional supported GGUF models: • OpenAI gpt-oss-20b — desktop-class local reasoning for suitable high-memory Apple silicon Macs • IBM Granite 4.2 3B — compact chat, coding and structured answers • LFM2-350M ENJP-MT — fast English–Japanese and Japanese–English translation • Mistral 7B Instruct v0.3 — general purpose and multilingual • DeepSeek R1 Distill Qwen 7B — reasoning for high-memory devices • DeepSeek R1 Distill Qwen 1.5B — compact reasoning • Qwen3 4B — larger multilingual model with thinking mode • NVIDIA Nemotron 3 Nano 4B — reasoning and coding • Phi-4 mini Instruct — instruction following and reasoning • Ministral 3 3B — chat, coding and instruction following • SmolLM3 3B — compact general-purpose model • TinySwallow 1.5B — Japanese-focused model from Sakana AI SEE WHAT’S ACTUALLY HAPPENING Most on-device AI apps hide the details. LemoLM shows them. • Performance Snapshot — measured loading and generation timing, token and speed estimates, device and operating-system details, memory readings, thermal state, battery and power context • Load Diagnostics — device memory, runtime mode and model file status when a model will not load • Full model details — size, runtime, quantisation, licence and source CONTROL THE OUTPUT • Precise, Balanced and Creative presets • Custom Temperature, Top-p, Top-k and Seed controls • Adjustable reasoning effort on supported models • Persistent settings with one-tap reset COMPARE AND KEEP • Rate models with your own stars and notes • Export a Performance Snapshot and conversation together, or export either separately, as Markdown • Learn about local AI concepts in the LLM Glossary PRIVATE BY DESIGN Conversations are stored on your device, and supported local models process prompts and responses on-device. Downloading a model requires internet access and may connect to third-party hosts such as Hugging Face. Once installed, supported downloadable models run locally. LemoLM collects no data. BEFORE YOU DOWNLOAD Performance depends on your device, available memory, operating system version, thermal state and model size. Compact models suit older or lower-memory devices. Larger GGUF models are best on recent Pro-class iPhones, M-series iPads and Apple silicon Macs. OpenAI gpt-oss-20b is intended for Apple silicon Macs with at least 24 GB of unified memory. Apple Foundation Models require a device that supports Apple Intelligence. Compact language models can hallucinate, misread prompts, lose context or state things that are incorrect. LemoLM is built for experimentation, learning and comparison. Always verify important information. Downloadable models are provided by their respective creators. Model availability, files, licences and download sources may change over time. Model names are trademarks of their respective owners. LemoLM is not affiliated with or endorsed by them.