These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.
About fullmoon
fullmoon runs large language models directly on Apple devices using Apple's MLX framework and Metal, so chats work offline and stay on the device. It offers models such as Llama 3.2 1B and 3B and DeepSeek R1 Distill Qwen 1.5B in quantised form, from about 0.7 GB to 1.8 GB.
You can adjust the theme, fonts and system prompt, and a Shortcuts action lets other automations get output from a local model. It is available on the App Store, with a TestFlight build for newer features.
Strengths
- Works fully offline on the device
- Optimised for Apple silicon with MLX
- Shortcuts integration
- Simple interface with customisable prompt
Limitations
- Apple silicon devices only
- Limited to a small set of small models
- Licence not stated on the homepage
Details
- Pricing
- FreeFree; described by the developer as open source.
- License
- Proprietary
- Developer
- Mainframe
- Platforms
- macOS, iOS
- How it runs
- Downloadable app
- Account
- Not required
- Works offline
- Yes
- Best suited for
- Private offline chat with a small LLM on an iPhone or Mac
- Categories
- Local AI tools, AI assistants
- Last verified
- Added
- Sources
Alternatives to fullmoon
Compare allSoftware that can replace fullmoon for an important use case, and what changes if you switch.
PocketPal AI
A mobile app for Android and iOS that downloads small language models and runs them on the phone.
PocketPal AI runs small language models on the phone and adds Android alongside iOS, but it has no Mac or Vision Pro version listed.
Private LLM
An offline AI chat app for iPhone, iPad and Mac that runs open language models on the device.
Private LLM is a paid, closed-source app for iPhone, iPad and Mac that works offline with Siri and Shortcuts integration, with one purchase covering all Apple devices.
Enclave AI
An iPhone, iPad and Mac app for chatting with open-source AI models that run offline on the device.
Enclave AI adds local voice chat, PDF and text file chat, and custom assistants on iPhone and Mac, but it is closed source.
Google AI Edge Gallery
A mobile and Mac app from Google for downloading and running generative AI models on-device.
Google AI Edge Gallery is Apache-2.0 and runs on Android, iPhone and Mac with Gemma 4 support and Agent Skills, but only allowlisted models, and it is a showcase app.
LLMFarm
An iOS and macOS app for running large language models offline on the device using GGML.
LLMFarm is an open-source iOS and macOS app built on GGML and llama.cpp, offering offline models without an account, though it is a small single-developer project.
Layla
An offline AI assistant app that runs language models directly on Android and iOS devices.
Layla moves to Android and iOS phones with character creation for role-play chats, uses a freemium model, is closed source and has no Mac version.
Similar software
Related functionality, not necessarily a direct replacement.
Ollamac
A native macOS app for chatting with language models served by a local Ollama installation.
RecurseChat
A macOS chat app for local AI models, with optional Claude and ChatGPT support.
LM Studio
A polished desktop app for downloading, running and chatting with local language models, with an OpenAI-compatible server built in.
MLX LM
A Python package and command-line tool for running and fine-tuning language models on Apple silicon.
ChatterUI
An Android front end for running language models on the phone or connecting to API providers.
Maid
A free, open-source app for chatting with llama.cpp models locally and remote AI providers.
