PocketPal AI

LLM Ventures

About this app

Your AI. No one else's.

PocketPal runs large language models directly on your phone. No servers. No internet. No data leaves your device. Ever.

This is AI you own — not AI you rent.

WHAT YOUR PHONE NEEDS

Modern phones are powerful enough to run real AI. PocketPal uses that power.

You'll need 6GB+ RAM for smaller models, 8GB+ for the good stuff. Flagship and recent mid-range phones from the last 2-3 years run models well. Older or budget devices won't cut it — this is real inference, not a cloud wrapper.

Not sure? Download a small model and benchmark it. The app will show you exactly what your device can handle.

WHAT YOU GET

- Hundreds of open-source models from HuggingFace, downloaded directly to your device
- Complete offline operation — airplane mode, no signal, underground, anywhere
- Zero data transmission. Zero telemetry. Verify it yourself: we're open source
- Full control over model parameters — temperature, context length, system prompts
- Built-in benchmarking to test model performance on your hardware
- Metal acceleration on iOS, NNAPI on Android
- Pals — AI personas from Palshub.ai that give models personality and purpose

WHAT THIS IS NOT

This is not ChatGPT. Cloud AI has trillion-parameter models running on server farms. Your phone runs smaller models locally. The trade-off is real — and it's one we're proud of.

You get something no cloud service can offer: conversations that exist only on your device, AI that works without internet, and complete freedom to run any model you choose. No content policies imposed by us. No behavioral guardrails we decided for you. Your rules.

WHO THIS IS FOR

People who stopped trusting the cloud with their conversations. People who want AI that works on a plane, in a tunnel, off the grid. People who care about what runs on their own hardware.

If you're looking for the "best" AI at any cost and don't care about privacy — use ChatGPT. It's great at what it does.

If you want AI that's yours, PocketPal is how you get it.

OPEN SOURCE

Every line of code is public on GitHub. Our privacy claims aren't marketing — they're verifiable. If you don't trust us, read the source. That's the point.

Ratings and reviews

I love it, the 2B models are the best if you ask me. It doesn't mess up your phone, mine's an S25 Ultra. I have no problems downloading and trying models. I wish they'd update pals, giving them their own pictures and stuff. Also, better TTS models, the ones they offer are trash. The option to use your own TTS isn't there, even though I heard it was.

⚠️ There's no point being proud that it can do this that and the other because in my experience I discover that ➡️ No instructions on how to set it up. Neither in his app nor anybody's YouTube videos. ⚠️ Very slow at replying. → One character at a time appears. It's like you can see typing one character at a time.

Dev's deserves more than 5 stars because it runs well, no adds and completely offline. There's a lot of model you can choose from so that your phone can run it smoothly... I've tried this and it is really great... More power to the Devs and make more improvements like, to make Ai remember or know from past chat context so Ai may learn and understand more so it won't start from scratch...

What’s new

• llama.cpp capability discovery: PocketPal now detects a connected server's vision support and context size, and warns when a chat runs out of room.
• Internet search in chat: Pals can search the web and read pages. Bring your own key (Brave, Tavily, Exa).
• Speculative decoding (experimental): pair a small draft model for faster replies.
• Pin chats, export chats as Markdown.
• Polish and Portuguese (PT), plus a searchable language picker.
• Updated llama.cpp engine.