Where to change it
Open Settings → AI Model to see what's installed and choose a different one.
Supported vs. bigger models
Models are grouped into two lists. Supported models are smaller and faster. Bigger / experimental models produce higher-quality suggestions but use more disk space and memory. If you're not sure, pick the recommended one.
The default is Gemma 4 E4B (about 6.2 GB), marked as the active model.
Download and offline use
When you select a model, TypeNext downloads it once to your Mac. After that, it runs entirely offline — no internet needed, no data sent anywhere. The download shows a percentage and estimated time remaining. If the download is interrupted, it resumes automatically from where it left off the next time you open TypeNext.
Writing Mode uses a separate model
When you turn on Writing Mode for an app, TypeNext downloads a separate, smaller model (Qwen 3 1.7B) on its own. It powers the faster Writing Mode path in those apps — same quality, quicker suggestions.
Everything TypeNext does — suggestions, Writing Mode, snippets, emoji, dictionary, read-aloud, style, and statistics — runs on your Mac. The only exception is Dictation, which can use cloud transcription. See the Dictation and Privacy guides for details.
