guinmoon/LLMFarm
iOS and MacOS app for running various LLMs locally offline.
Not currently ranked — collecting fresh signals.
star history
LLMFarm is a native iOS and MacOS application that enables local execution of large language models including LLaMA, Gemma, GPT-NeoX, RWKV, and StarCoder. It is built on top of the GGML library and llama.cpp for efficient inference, utilizing Metal for GPU acceleration on Apple silicon. The app supports various sampling methods, model parameter configuration, context state saving and restoration, and includes RAG capabilities for retrieval-augmented generation.
Frequently asked
- What is guinmoon/LLMFarm?
- iOS and MacOS app for running various LLMs locally offline.
- Is LLMFarm open source?
- Yes — guinmoon/LLMFarm is open source, released under the MIT license.
- What language is LLMFarm written in?
- guinmoon/LLMFarm is primarily written in C.
- How popular is LLMFarm?
- guinmoon/LLMFarm has 2k stars on GitHub.
- Where can I find LLMFarm?
- guinmoon/LLMFarm is on GitHub at https://github.com/guinmoon/LLMFarm.