#149 · Primary category： Inference & Local Deploy
LLMFarm
llama and other large language models on iOS and MacOS offline using GGML library.
Project last updated：01/30/26
GitHub Stars
2.1K
Forks
180
Contributors
1
License
MIT
Why we included this project
LLMFarm runs language models natively on iPhone, iPad, and Mac with no cloud round-trip, which is the whole point for anyone who wants to keep prompts and documents on the device. It wraps llama.cpp and GGML and supports a broad set of open models: LLaMA, Gemma, Qwen, DeepSeek, Mixtral, Mamba, and RWKV, plus multimodal options like LLaVA and Moondream. Beyond plain chat, you get fine-grained control over sampling (temperature, top-p, mirostat, grammar), model templates, context-state restore, Apple Shortcuts, and even RAG. For teams trying to decide whether a model can run well on a phone or a laptop, it doubles as a benchmark tool to compare speed and memory use on real Apple silicon before making a choice.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
llama.cpp
LLM inference in C/C++
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.