Run NameQuick Fully Local

NameQuick can run entirely on your Mac. Point it at a local model served by Ollama, LM Studio, or MLX, and file contents are analyzed on your own hardware — nothing is sent to any cloud provider. No API key, no per-rename cost, works offline.

This is the right setup if you rename confidential material (contracts, medical or financial documents, client files) or simply want a one-time purchase with zero running costs.

What to expect: local models are slower than cloud models and small ones produce simpler filenames. On Apple Silicon with a mid-size model, quality is very usable for documents; for image-heavy work you'll need a vision-capable model. Try your real files during the trial and judge for yourself.

---

Option 1: Ollama (recommended start)#

Ollama is the easiest way to run local models on a Mac.

1. Download Ollama from ollama.com and install it.
2. In Terminal, pull a model. For documents and images, pick a vision-capable model — for example: ollama pull gemma3 (vision-capable models can read scans and photos; text-only models handle documents only).
3. Open NameQuick → Settings → AI and select Ollama. The default server address (http://127.0.0.1:11434) matches Ollama's standard setup — you usually don't need to change anything.
4. Choose your pulled model and rename a test file.

If your model is text-only, NameQuick can still rename documents via extracted text, but images and scanned PDFs need a vision model — you'll see a message telling you so.

Option 2: LM Studio#

LM Studio gives you a graphical app for browsing and running models.

1. Install LM Studio, download a model inside it, then start the local server (LM Studio's server runs at localhost:1234 by default).
2. In NameQuick → Settings → AI, select LM Studio and confirm the server address.
3. Pick the loaded model and test with one file.

Option 3: MLX (Apple Silicon)#

MLX is Apple's machine-learning framework, optimized for M-series chips. Select MLX in Settings → AI and NameQuick manages the runtime for you — no separate server app to install. Requires an Apple Silicon Mac.

---

Local vs. cloud at a glance#

You can switch providers anytime in Settings → AI — many people use a local model for sensitive folders and a cloud model for everything else. For exactly what leaves your Mac in each mode, see Privacy & Your Data.

---

Common issues#

NameQuick can't reach the model — make sure Ollama is running (menu bar icon) or LM Studio's server is started, and the address in Settings → AI matches.

Images or scans aren't being renamed — your model is text-only. Pull a vision-capable model and select it.

Renames are slow — bigger models are slower; try a smaller one, or close other heavy apps. Apple Silicon is dramatically faster than Intel here.

More in Troubleshooting.