Local AI
Learn how RenamerX local AI performance profiles work and when to switch between them.
Local AI
RenamerX uses a local AI runtime, so the selected performance profile influences quality, speed, and resource efficiency.
Most users should leave the defaults alone. This page is for the cases where you need to tune performance or stability.
What RenamerX installs locally
After first launch, RenamerX prepares the local resources needed for on-device AI processing and media analysis, including:
- A local AI processing engine
- Model resources for document and image understanding
- Media-analysis components used by video workflows
Performance profiles in Preferences
Preferences now exposes a single Local AI control: the performance profile.
Use it to choose how much resource the local AI should use. If the local AI is already running, stop it and start it again to apply the new profile.
Performance mode
RenamerX includes three performance profiles:
| Profile | Best for | Notes |
|---|---|---|
| Low Memory | Smaller or more constrained machines | Uses less memory and is the safest starting point when the app feels heavy. |
| Balanced | Most devices | The default profile and the best starting point for most users. |
| High Performance | Stronger hardware | Prioritizes throughput and speed when your machine can handle more load. |
These profiles are intentionally simple. RenamerX applies the lower-level runtime tuning internally.
Low Memory
Use this when memory is tight or when you want the most conservative behavior.
Balanced
The default profile. This is the right starting point for most users.
High Performance
Best when you have stronger hardware and want more throughput.
Recommended tuning patterns
If the app feels heavy
- Switch to Low Memory
- Restart the local AI if it is already running
If image and video naming feels weak
- Keep Balanced or High Performance
- Make sure local resources finished downloading completely
If you are processing mixed media all day
- Stay on Balanced first
- Change one profile at a time
- Measure stability before enabling more parallel work
A practical rule
Do not try to fine-tune individual runtime knobs. Pick the profile that matches your machine, run a real batch, and judge the result with your own files.