Which model should you use?

Local models

Local models live on your computer. Once you download one, your messages stay on the machine. There's no internet round-trip when you press send. They're free and work offline.

The trade-off is hardware. PearPie ships a lightweight local model that runs on most machines (RAM is the main requirement, no GPU needed), and a larger one that needs a GPU and is noticeably faster and more capable on complex reasoning. More open-source options on the way.

Best for: everyday questions, casual brainstorming, anything you'd want to keep entirely on your own machine.

Peer-to-peer (a device you trust)

If you've linked another device, you can use a model that lives on that device from whatever you happen to be holding. Nothing runs on the device in your hand: the model stays where it is, and only the conversation travels, directly between the two devices over an encrypted connection with no server in the middle.

The other device doesn't have to be yours. It can be a desktop at home, a workstation at the office, or a colleague's or friend's machine, as long as they've linked with you and are happy to share it. Either way you're reaching a stronger model that already exists somewhere you trust, rather than squeezing more out of your own hardware. It only works while that device is on and connected.

Best for: using a model your current device can't run, on hardware you or someone you trust already owns, without spending credits.

Premium models (PearPie Network)

The PearPie Network is for models you can't or don't want to host yourself. Some are closed-source frontier models that can only be accessed through a hosted provider. Others are open-source but heavy enough that running them locally isn't practical for most people. Underneath, the PearPie Network uses the same peer-to-peer mechanism as connections between your own devices: PearPie joins your device network as a trusted device that runs those models on European infrastructure. Your message is discarded after the reply. PearPie doesn't store the request, and providers retain nothing permanently.

Premium models cost credits. They're worth it when you want the absolute best response on a hard question, a long document, or a precise piece of writing. They're also useful if your hardware just isn't up to running a local model that's good enough for what you're trying to do. See pricing →

Best for: harder problems, longer or more nuanced conversations, anything where you want the strongest available answer, or anytime your local hardware can't keep up.

Quick cheat sheet

If you're not sure, this is the rough order to try:

• Casual question? Local model. Fast, free, completely private.
• On your phone and need a stronger model? Use one running on a linked desktop.
• Local model too slow or struggling? Premium model. Same goes for older or lower-spec hardware that can't run the bigger local options.
• Tricky problem or long document? Premium model. Worth a credit or two.

You can always switch mid-conversation if a local model is struggling. The model picker is right there at the top of the chat window.