Components All New MacOS Windows Linux iOS
Examples Mac & Win Server Client Guides Statistic FMM Blog Deprecated Old

Llama.LoadModel

Load the model from a file.

Component Version macOS Windows Linux Server iOS SDK
Llama 16.1 ✅ Yes ✅ Yes ✅ Yes ✅ Yes ✅ Yes
MBS( "Llama.LoadModel"; LlamaSession; Path { ; Options } )   More

Parameters

Parameter Description Example Flags
LlamaSession The session identifier. $$session
Path The native path to the model. "/Users/cs/gemma-3-1b-it.Q8_0.gguf"
Options The JSON with parameters.
Optionally you can pass a number for n_gpu_layers or main_gpu.
n_gpu_layers: number of layers to store in VRAM, a negative value means all layers		 Optional

Result

Returns OK or error.

Description

Load the model from a file.
If the file is split into multiple parts, the file name must follow this pattern: <name>-%05d-of-%05d.gguf
e.g. gemma-3-1b-it.Q8_0.gguf or gpt-oss-20b-Q4_K_M.gguf

Examples

Load a model on macOS:

Set Variable [ $path ; Value: "/Users/cs/gemma-3-1b-it.Q8_0.gguf" ]
Set Variable [ $r ; Value: MBS("Llama.LoadModel"; $$session; $path) ]
If [ MBS("IsError") ]
    Show Custom Dialog [ "Failed to load model." ; $r ]
End If

Load a model on Windows:

Set Variable [ $path ; Value: "C:\Users\User\Modesl\gemma-3-1b-it.Q8_0.gguf" ]
Set Variable [ $r ; Value: MBS("Llama.LoadModel"; $$session; $path) ]
If [ MBS("IsError") ]
    Show Custom Dialog [ "Failed to load model." ; $r ]
End If

See also

Example Databases

Blog Entries

Created 10th February 2026, last changed 16th February 2026


Llama.LoadLibrary - Llama.Loaded