.svg)
Liquid AI announces LEAP, our developer platform for building with on-device AI—and Apollo, a lightweight iOS application for vibe checking small language models directly on your phone.
With LEAP and Apollo, AI isn’t tied to the cloud anymore. Run it locally when you want, for speed, privacy, and reliability, using LEAP’s end-to-end toolkit for on-device AI.
What We’re Launching
LEAP: The Liquid Edge AI Platform
LEAP is a developer-first platform for AI on the edge that is proudly OS- and model-agnostic. With initial support for both Android and iOS, it enables developers to deploy small language models (SLMs) directly in their mobile apps with just a few lines of code. Built to make edge AI accessible to everyone, LEAP radically simplifies what once required deep expertise, complex tooling, and heavy infrastructure.
Core Features:
- Run local models with the same simplicity as calling a cloud API.
- Cross-platform Edge SDKs available for Android and iOS.
- Lightweight model library featuring SLMs like LFM2, with more on the way.
- Optimized model sizes as small as 300MB — built for mobile and edge.
- Runs smoothly on devices with 4GB+ RAM.
- Designed for efficiency — minimal battery use, maximum speed.
Apollo: Try Private AI, On Your Phone
Earlier this year, Liquid acquired Apollo, a fully private AI chat mobile application, as part of our mission to bring capable AI to every device at every scale.
And now, Apollo has native support for all LEAP models, to enhance not only the Apollo user experience, but the LEAP developer experience as well. This reimagined app allows users to interact with the entire LEAP model library – including Liquid’s new generation of LFM2 models – in a fully offline, privacy-preserving interface.
Whether you’re a developer looking to vibe-check model tone and test efficiency live in your hand, or a user exploring the potential of private AI, Apollo gives you a low-latency, cloud-free playground in your pocket with no barrier to entry.
“Our research shows developers are moving beyond cloud-only AI and looking for trusted partners to help them build on-device," said Ramin Hasani, co-founder and CEO of Liquid AI. "LEAP is our answer—a flexible, end-to-end deployment platform built from the ground up to make powerful, efficient, and private edge AI truly accessible. And with Apollo, our native iOS app, users can easily test our latest small language models right on their phones. We hope developers enjoy building with these tools as much as we do."
Built for Developers...
- Teams blocked by fragile or underperforming small model
- Cloud API users frustrated by cost, privacy, or connectivity
- Devs who want the fastest path to edge AI models that just work
...By Developers
- No ML expertise needed: Integrate local edge models into your mobile app as easily as calling a cloud API
- Open and Interactive: Get the best performance for YOUR real-world scenario, without barriers or lock-in to a particular platform or model provider
- One-stop-shop for edge models: Discover, adapt, test, and deploy - all in one interconnected ecosystem
Unified Platform
Large models are generalists — they do many things well. Small models, by contrast, are either average at many tasks or excellent at a few.
That’s why LEAP offers a curated library of diverse small models, checkpoints, and quantization options — so developers can find the right fit for their specific on-device use case.
And it doesn’t stop there: LEAP is also your all-in-one platform for tuning, adapting, and deploying SLMs directly on-device.
How to Get Started
- Start vibe checking models and using private, offline AI today: Download Apollo on iOS
- Begin building and deploying AI solutions to the edge with LEAP: Explore LEAP SDK
- Be a part of our Developer Community, where we host Office Hours, run competitions, and share updates: Join Discord