Skip to content

Models and assignments

Curator runs every AI feature on local models through Ollama. Instead of one model doing everything, Curator assigns a model to each task. You can change any assignment in Settings under AI & Models.

TaskWhat it powers
Vision / AnalysisReads images and scanned PDFs so their content becomes searchable.
OCRPulls text out of scanned documents and images.
EmbeddingsTurns text into meaning, which powers search by meaning and the documents chat draws from.
ChatAnswers your questions and cites the files it used.
File ProcessingWrites the AI description, category, and other metadata for each file.
OrganizationGroups files into clusters on the Organize screen.

Models are downloaded, or pulled, through Ollama. Curator can pull its recommended models straight from Settings under AI & Models.

These are the models Curator suggests out of the box. Vision and OCR share one model, and File Processing and Organization share another, so four downloads cover all six tasks.

TaskDefault modelApprox. download
Vision / Analysisminicpm-v4.56.1 GB
OCRminicpm-v4.5 (same as Vision)shared
Embeddingsnomic-embed-text-v2-moe1.0 GB
Chatqwen3.5:9b-mlx8.9 GB
File Processingmaternion/lfm2.55.2 GB
Organizationmaternion/lfm2.5 (same as File Processing)shared

Sizes are the on-disk download and are approximate. Ollama confirms the exact size on the first pull.

Onboarding reads how much memory your Mac has and warns before you pull a model that looks too large, using a rough rule of leaving about a third of your memory free for the system and other apps. The warning does not block the download, it just flags that the model may load slowly or run out of memory. Larger models are more capable but use more memory, and processing more files at once uses more still.

Curator talks to Ollama at a single address, the Ollama Base URL. The default is http://localhost:11434, which is Ollama running on the same Mac. You can point it at Ollama on another computer on your network instead.

The connection test in Settings shows one of four states.

BadgeMeaning
Not testedYou have not run the test yet.
TestingThe test is in progress.
ConnectedCurator reached Ollama and AI features are available.
OfflineCurator could not reach Ollama. AI features stay off until it can.

To understand what Ollama is and why Curator depends on it, read Ollama and models.