1# llama.cpp/examples/llama.swiftui
 2
 3Local inference of llama.cpp on an iPhone. This is a sample app that can be used as a starting
 4point for more advanced projects.
 5
 6For usage instructions and performance stats, check the following discussion: https://github.com/ggml-org/llama.cpp/discussions/4508
 7
 8
 9### Building
10First llama.cpp need to be built and a XCFramework needs to be created. This can be done by running
11the following script from the llama.cpp project root:
12```console
13$ ./build-xcframework.sh
14```
15Open `llama.swiftui.xcodeproj` project in Xcode and you should be able to build and run the app on
16a simulator or a real device.
17
18To use the framework with a different project, the XCFramework can be added to the project by
19adding `build-apple/llama.xcframework` by dragging and dropping it into the project navigator, or
20by manually selecting the framework in the "Frameworks, Libraries, and Embedded Content" section
21of the project settings.
22
23![image](https://github.com/ggml-org/llama.cpp/assets/1991296/2b40284f-8421-47a2-b634-74eece09a299)
24
25Video demonstration:
26
27https://github.com/bachittle/llama.cpp/assets/39804642/e290827a-4edb-4093-9642-2a5e399ec545