| Components | All | New | MacOS | Windows | Linux | iOS | ||||
| Examples | Mac & Win | Server | Client | Guides | Statistic | FMM | Blog | Deprecated | Old | |
Llama.LoadBackend
Loads a backend for Llama from the given location.
| Component | Version | macOS | Windows | Linux | Server | iOS SDK |
| Llama | 16.2 | ✅ Yes | ✅ Yes | ✅ Yes | ✅ Yes | ✅ Yes |
MBS( "Llama.LoadBackend"; Path ) More
Parameters
| Parameter | Description | Example |
|---|---|---|
| Path | The native file path to the backend file. | "/test/libggml-metal.dylib" |
Result
Returns OK or error.
Description
Loads a backend for Llama from the given location.By default we load all backends. But if you have a separate library somewhere else, you can explicitly load it here.
Release notes
- Version 16.2
- Added Llama.LoadBackend function.
Blog Entries
This function is free to use.
Created 18th March 2026, last changed 18th March 2026
