Skip to main content
Model is where you choose the local model Chat and Personas use on this computer. Click your name at the bottom of the sidebar, then Settings, then Model. Picking a model does not download it yet. Apply starts the download and load.

​
Choose a model

1

Open Model

Click your name at the bottom of the sidebar, then Settings, then Model.
2

Open the catalog

Click the model field. Pick a family, then a size. Some models also ask you to pick a quantization. Models are listed by their catalog display names, not raw repository ids. Each row shows whether that model can accept images.
3

Check that it fits

Each choice shows how much memory it needs. A laptop mark means that model is already on this computer. A download mark means it is not. The footer shows free disk space.
4

Apply

Click Apply. Progress appears in the header as Downloading model or Loading model, with a percent. A model published in several parts shows which part is in progress.
If that model is already loaded, Apply stays off until you pick a different one. While the same model is downloading, click Apply again to stop it.
Thinking mode appears when the selected model can show its reasoning. It starts on. Leave it on to get Thinking and Thought process in Chat. Turn it off to skip that reasoning step.
Some catalog models need a Hugging Face token before the first download. Save the token when the form appears, then click Apply.

​
New and removed models

  • New in the catalog: TwIL 3B Pro, TwIL 2B, and Granite 4.2 8B.
  • Default on 8 GB Macs: TwIL 3B Pro.
  • Removed from the catalog: Llama 3.2, Gemma 3 1B, and Granite 4.1. If you downloaded one of these, webAI deletes its files to free up disk space. Pick another model and click Apply.

​
Idle memory

On Macs with 16 GB of memory or less, the chat model frees its memory after 5 idle minutes. The next reply takes about 2 seconds longer to start while the model loads again. The model that searches your documents also frees its memory after 5 idle minutes on many Macs. If the chat model stops unexpectedly, webAI starts it again on its own. You do not have to restart the app.

​
Personas on this page

The Persona list is on the same Settings page. Local Personas use the model you applied above. Click + New Persona to create one, or open a row to edit it. For chatting with a Persona and the full create flow, see Personas.

​
Common questions

No. Picking a model in Settings → Model does not download it yet. Click Apply to start the download and load. Progress appears in the header as Downloading model or Loading model.
Open the model field and browse the catalog. Models use catalog display names. Each row shows whether that model can accept images, and how much memory it needs. A laptop mark means that model is already on this computer. A download mark means it is not. The footer shows free disk space.
Thinking mode appears when the selected model can show its reasoning. It starts on. Leave it on to get Thinking and Thought process in Chat. Turn it off to skip that reasoning step.
Some catalog models need a Hugging Face token before the first download. Save the token when the form appears, then click Apply.
Llama 3.2, Gemma 3 1B, and Granite 4.1 were removed from the catalog. If you downloaded one of them, webAI deletes its files to free up disk space. Pick another model and click Apply.
On Macs with 16 GB of memory or less, the chat model frees its memory after 5 idle minutes. The next reply takes about 2 seconds longer to start. See Idle memory.