ModelFilePath

ModelFilePath is the highest-priority source for the model file. When set to a non-empty path, the engine loads directly from disk and skips all download logic.

Quick reference


Type	`string?`
Default	`null`
Priority	1 (takes precedence over the Hugging Face source)
Category	Model source
Field on	`ModelSourceParameters.ModelFilePath`

What it does

null or empty: the configured Hugging Face source may be used. AsposeModelId is reserved and ignored.
A path: load the GGUF from that file. No download.

The file must be accessible and readable by the process.

When to change it

Scenario	Value
Use the configured Hugging Face source	`null`
Air-gapped deployment with pre-downloaded model	Absolute path
Custom local GGUF	Path to the file
Testing a model before mirroring to Hugging Face	Local path

Example

var preset = new Qwen25Preset();
preset.BaseModelSourceParameters.ModelFilePath =
    @"C:\models\Qwen2.5-7B-Instruct-Q4_K_M.gguf";
// Bypass the Hugging Face values on the preset.

using var api = AsposeLLMApi.Create(preset);

Interactions

AsposeModelId: reserved and ignored.
HuggingFaceRepoId + HuggingFaceFileName: priority 3; ignored when ModelFilePath is set.
EngineParameters.ModelCachePath: cache is not used when loading from an explicit ModelFilePath.

What’s next

Model source hub: resolution order overview.
Bring your own GGUF: full custom-model workflow.
Offline deployment: air-gapped setup.

AsposeModelId