Cotabby logo
Cotabby

Help · Settings

choose the right local autocomplete engine

Compare Apple Intelligence and local GGUF engines in Cotabby, choose a curated model, import your own GGUF, or use models already stored by LM Studio.

By Jacob Fu · Updated · 9 minute read

Engine and model choices live in Cotabby Settings and remain local to the Mac.

Apple Intelligence or Open Source?

ConsiderationApple IntelligenceOpen Source
RequirementsSupported Mac, macOS 26+macOS 14+, Apple Silicon recommended
DownloadNo separate model fileA local GGUF file
Model choiceManaged by AppleCurated or user-selected
OfflineYes when availableYes after download

curated local models

ModelApproximate sizeStarting guidance
tabby-2-nano0.8 GBFastest option for older or lower-memory Macs
tabby-2-mini1.4 GBBalanced everyday starting point
tabby-2-base4.5 GBLarger local model with higher memory use
tabby-2-pro5.0 GBLargest curated model and the heaviest local option

A larger file is not automatically better autocomplete. If it cannot keep up with normal typing, a smaller model produces the more useful experience even when its individual completions are less ambitious.

bring another GGUF model

  • Open Settings → Engine & Model.
  • Use the built-in Hugging Face browser or open Cotabby's models folder.
  • Download or copy a compatible .gguf file into that folder.
  • Choose Refresh, then select the discovered model.

reuse LM Studio models

Enable “Also Use LM Studio Models” in Engine & Model to include GGUF files already stored in the local LM Studio library. Cotabby reads the files locally; it does not require LM Studio to generate each suggestion.

If LM Studio moves or removes a file, refresh Cotabby's model list and select an available model again.

switch by power source

Cotabby can select a different engine or local model on battery and while plugged in. A smaller battery model can reduce memory and energy use while a larger plugged-in model prioritizes completion quality.

Configure both profiles before enabling the switch so moving between power states never lands on a missing model.

offline and network behavior

In the public release documented here, generation uses Apple Intelligence or an in-process local GGUF model. Network access is used for update checks, Hugging Face search, and model downloads—not for the text-generation request itself.

Read the full security and data-flow model or troubleshoot a model that will not load.

related help

try Cotabby on your Mac

Free, open source, and local. Use Apple Intelligence or a GGUF model, then accept the next word with Tab.

View source