Ask LM Mini (On-Device)
Dictate a question and get a spoken answer from a model running entirely on your device. No internet required after the model is downloaded.
One-tap install
Build the shortcut below (2 minutes), then share to iCloud from Shortcuts.app to enable one-tap install for others. Update website/data/shortcuts.json with your icloudUrl and re-run this generator.
Siri Phrase
"Hey Siri, ask LM Mini"
Run once after installing, then Siri learns this phrase.
How the shortcut works
- Dictate your question.
- LM Mini runs the prompt on your downloaded on-device model.
- The answer is spoken aloud and copied to clipboard.
- Works in airplane mode.
Key features
- Forces on-device inference — no cloud fallback
- Action Button mapping on iPhone Pro
- Uses your global on-device model from LM Mini settings
- Fast with Llama 3.2 1B or Qwen 3 4B
Recommended models
Llama 3.2 1B (free), Qwen 3 4B (8 GB+)
Qwen 3 8B (MLX) on M-series iPad and Mac
Tune temperature (0.7) and top-p (0.9) in LM Mini → Settings → Model Parameters. See the full on-device model catalog.
Build it in 60 seconds
- Add Dictate Text.
- Add Ask LM Mini — enable On-Device, pass Dictated Text.
- Enable Speak answer aloud.
- Map to Action Button in Settings.
URL scheme (power users)
Add an Open URLs action in Shortcuts.app:
lmmini://shortcut/ask?prompt=YOUR_PROMPT&onDevice=1&speak=1Need LM Mini? Free on iOS and Android — on-device GGUF/MLX, LM Studio Connect, voice, and more.
Download LM Mini LM Mini vs Private LLM