LLMFarm
An iOS and macOS app for running large language models offline on the device using GGML.
These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.
About LLMFarm
LLMFarm lets you load and chat with LLaMA and other large language models directly on an iPhone, iPad or Mac, with no server involved. It is built on the GGML library used by llama.cpp, so models run offline on the device's own hardware.
The repository also contains test projects for LLaVA image models, fine-tuning and retrieval-augmented generation on iOS, which points to experimental support for those features. It suits Apple users who want to try local models on a phone or laptop.
Strengths
- Runs models fully offline on iPhone, iPad and Mac
- Based on the widely used GGML and llama.cpp stack
- No account or server needed
Limitations
- Apple platforms only
- Large models are limited by the memory of mobile devices
- Small single-developer project
Details
- Pricing
- FreeFree, with source code published on GitHub.
- License
- Open source, license not stated
- Developer
- guinmoon
- Platforms
- macOS, iOS
- How it runs
- Downloadable app
- Account
- Not required
- Works offline
- Yes
- Best suited for
- Apple users who want to run language models locally on a phone or Mac
- Categories
- Local AI tools
- Last verified
- Added
- Provenance
- Facts checked against the developer's own pages and store listings, 1 sources on file.
Alternatives to LLMFarm
Compare allSoftware that can replace LLMFarm for an important use case, and what changes if you switch.
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 adds Siri and Shortcuts integration.
PocketPal AI
A mobile app for Android and iOS that downloads small language models and runs them on the phone.
PocketPal AI runs small models on iOS and Android phones, but has no Mac version listed and is not open source.
Layla
An offline AI assistant app that runs language models directly on Android and iOS devices.
Layla is a freemium, closed source offline assistant for iOS and Android with character creation, without a Mac app.
LM Studio
A polished desktop app for downloading, running and chatting with local language models, with an OpenAI-compatible server built in.
LM Studio covers the Mac side with a polished desktop app using MLX and llama.cpp, but is closed source and has no iOS app.
Similar software
Related functionality, not necessarily a direct replacement.
llama.cpp
The C++ engine most local AI apps are built on, running language models on ordinary hardware.
MLX LM
A Python package and command-line tool for running and fine-tuning language models on Apple silicon.
Ollamac
A native macOS app for chatting with language models served by a local Ollama installation.
Ollama
The simplest way to pull down an open language model and run it on your own machine, from one command or a desktop app.
