GgufModelConfig class

Configuration for loading a pre-quantised GGUF model.

Constructors

GgufModelConfig({required String modelId, required List<String> files, String? tokModelId, required String displayName, required String approxMemory})

const

Properties

approxMemory → String

Approximate memory footprint, e.g. "~941 MB (GGUF Q4_K_M)".

final

displayName → String

Human-friendly display name, e.g. "Qwen 2.5 1.5B".

final

files → List<String>

GGUF filename(s) within the repository.

final

hashCode → int

The hash code for this object.

no setter, override

modelId → String

HuggingFace repository ID, e.g. "bartowski/Qwen2.5-1.5B-Instruct-GGUF".

final

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

tokModelId → String?

Optional explicit tokenizer model ID (required on Android).

final

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

override