OneNmModel class
Registry of pre‑configured models that can be used with OneNm.
Each static constant is a ModelInfo describing a specific GGUF model hosted on HuggingFace. Pass one of these to OneNm to use a model:
final ai = OneNm(model: OneNmModel.tinyllama);
To add a custom model, create your own ModelInfo instance.
Properties
- hashCode → int
-
The hash code for this object.
no setterinherited
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
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.
inherited
Constants
-
all
→ const List<
ModelInfo> - List of all built-in models.
- gemma2b → const ModelInfo
- Google Gemma 2B IT — lightweight instruction‑tuned model.
- llama32 → const ModelInfo
- Meta Llama 3.2 3B Instruct — capable multilingual model.
- mistral7b → const ModelInfo
- Mistral 7B Instruct v0.2 — high‑quality 7B instruction model.
- phi2 → const ModelInfo
- Microsoft Phi‑2 2.7B — more capable but requires extra RAM.
- qwen25 → const ModelInfo
- Qwen2.5 1.5B Instruct — compact multilingual model with strong coding.
- tinyllama → const ModelInfo
- TinyLlama 1.1B Chat — lightweight model suitable for most phones.