Elephas now offers multiple ways to run AI models offline, giving you complete control over your data privacy and performance. Choose the option that best fits your needs.

The simplest way to go offline! Elephas now comes with pre-integrated offline AI models that require absolutely no technical setup. Just select, download with one click, and start using immediately. You need Apple Silicon (M1 and later) to use this feature.

The primary way to leverage Elephas offline models is through Brain creation.

Perfect for users who want instant offline AI without any technical setup!

💡 For detailed information about Elephas offline models, check out our comprehensive Elephas Inbuilt Offline Models guide.

There are two external apps you can use for offline AI models:

In this section, we will focus specifically on Jan.ai  setup and integration.

Jan.ai makes things easy: download AI models straight to your server for better security, skipping the risky unknowns.

Simple privacy! And it works with both Intel and Silicon chips.

visit the page Jan.ai to set up on your Mac

After installing Jan.ai → Hub→ Search the model is, ”Llama-3-8B-Instruct-32k-v0.1-GGUF”

There are many AI models available in the Jan.ai(Offline AI), we suggest to use, Llama3 quantised model from here,

Click a “Download” And “Use” it,

Click the “Start Server” button,

Now go to Elephas → Preference → AI Providers → Custom AI, and Enter your local host url (Authorization is optional).

Now go to Elephas → Preference → Model Settings. Now you can pick a feature and select any Jan.ai (Offline AI) models available from dropdown.

In Super Chat as well, you can select the Jan.ai( Offline AI) models

Super brain indexing still requires internet connection as it depends on backend AI engine, we will add the offline capability soon.

Need help? We're Here for You!

Contact us in support@elephas.app.