LLM Farm
A local LLM app runs text and vision models offline on iOS and macOS, with Apple Shortcuts integration and an MIT license.
LLM Farm is an app for on-device AI conversations and comparing language models on Apple hardware. It suits people who want offline chat or need to assess which model fits a project.
- Text and vision models: Use text models such as LLaMA, Gemma, Phi, Qwen, Deepseek and Mixtral MoE, or image-capable models including LLaVA, BakLLaVA, MobileVLM, Yi-VL and Moondream.
- Reference material: Retrieval-augmented generation (RAG) lets conversations draw on reference material.
- Model comparison: Reusable settings templates and sampling controls let you test response behavior, including grammar constraints and Mirostat sampling.
- Saved context: Restore context state to continue a conversation with its earlier context.
- Apple Shortcuts: Connect the app to automations on Apple devices.
Inference runs locally without an internet connection, using ggml and llama.cpp. The app is open source under the MIT license and supports iOS 16 or later and macOS 13 or later. It can use Metal GPU acceleration, but that support doesn't work on Intel Macs.
The app is temporarily unavailable through TestFlight and the App Store.
Logotyper
