Select a model by task
Match a built-in preset to the task. Start small; move up only if output quality does not meet your bar.
No built-in LLM is included in Aspose.LLM. The library is a local inference runtime: you choose which open source model to use, and the model file is obtained separately and stored on your own machine. Model files are covered by the license of the model publisher, not by your license agreement with Aspose Pty Ltd.
Check the license of the model a preset resolves to before using it commercially. Licenses are listed in Supported presets.
Quick picker
| Your task | Preset |
|---|---|
| General chat, mid-complexity tasks | Qwen25Preset (7B) |
| Latest general-purpose model | Qwen3Preset (8B) |
| Small footprint, fast, long context | Llama32Preset (3B, 131K) |
| Smallest possible model | Phi4Preset (mini) |
| Coding tasks | DeepSeekCoder2Preset |
| Step-by-step reasoning | DeepseekR1Qwen3Preset |
| Largest model, strongest reasoning | SeedOss36BPreset (36B) |
| Image understanding, small | Qwen3VL2BPreset (2B) |
| Image understanding, mid | Glm4_6VFlashPreset |
| Text-heavy images (OCR-style) | Ministral3VisionPreset |
| Strongest vision reasoning | Ministral3VisionPreset (8B) |
Decision tree
-
Do you need vision (image input)?
- Yes → pick a vision preset based on size and image type.
- No → continue.
-
Is the task coding?
- Yes →
DeepSeekCoder2Preset. - No → continue.
- Yes →
-
Does the task require explicit step-by-step reasoning?
- Yes →
DeepseekR1Qwen3PresetorOss20Preset(budget 1024-2048MaxTokens). - No → continue.
- Yes →
-
How much memory do you have?
- 4-8 GB →
Llama32PresetorPhi4Preset. - 12-16 GB →
Qwen25PresetorQwen3Preset. - 24+ GB → any preset;
Oss20Presetfor best quality.
- 4-8 GB →
After you pick
Override the default values where they do not fit your scenario. See Customizing presets.
If none of the built-ins fit, bring your own GGUF.
Before you ship
What’s next
- Supported presets: catalog with Hugging Face sources.
- Using built-in presets: full picker guidance.
- Custom preset: patterns for tuning.