Need smarter insights in your inbox? Join our weekly newsletters to get solely what issues to enterprise AI, knowledge, and safety leaders. Subscribe Now
Liquid AI, the startup fashioned by former Massachusetts Institute of Know-how (MIT) researchers to develop novel AI mannequin architectures past the widely-used “Transformers“, as we speak introduced the discharge of LEAP aka the “Liquid Edge AI Platform,” a cross-platform software program improvement package (SDK) designed to make it simpler for builders to combine small language fashions (SLMs) instantly into cellular functions.
Alongside LEAP, the corporate additionally launched Apollo, a companion iOS app for testing these fashions regionally, furthering Liquid AI’s mission to allow privacy-preserving, environment friendly AI on shopper {hardware}.
The LEAP SDK arrives at a time when many builders are in search of options to cloud-only AI providers as a result of considerations over latency, value, privateness, and offline availability.
LEAP addresses these wants head-on with a local-first method that permits small fashions to run instantly on-device, decreasing dependence on cloud infrastructure.
The AI Impression Sequence Returns to San Francisco â August 5
The subsequent section of AI is right here â are you prepared? Be part of leaders from Block, GSK, and SAP for an unique have a look at how autonomous brokers are reshaping enterprise workflows â from real-time decision-making to end-to-end automation.
Safe your spot now â area is restricted: https://bit.ly/3GuuPLF
Constructed for cellular devs with no prior ML expertise required
LEAP is designed for builders who need to construct with AI however could not have deep experience in machine studying.
Based on Liquid AI, the SDK might be added to an iOS or Android venture with only a few strains of code, and calling an area mannequin is supposed to really feel as acquainted as interacting with a standard cloud API.
“Our analysis reveals builders are shifting past cloud-only AI and searching for trusted companions to assist them construct on-device,” mentioned Ramin Hasani, co-founder and CEO of Liquid AI, in a weblog submit asserting the information as we speak on Liquid’s web site. “LEAP is our reply—a versatile, end-to-end deployment platform constructed from the bottom as much as make highly effective, environment friendly, and personal edge AI actually accessible.”
As soon as built-in, builders can choose a mannequin from the built-in LEAP mannequin library, which incorporates compact fashions as small as 300MB — light-weight sufficient for contemporary telephones with as little as 4GB of RAM (!!) and up.
The SDK handles native inference, reminiscence optimization, and machine compatibility, simplifying the everyday edge deployment course of.
LEAP is OS- and model-agnostic by design. At launch, it helps each iOS and Android, and presents compatibility with Liquid AI’s personal Liquid Basis Fashions (LFMs) in addition to many widespread open-source small fashions.
The objective: a unified ecosystem for edge AI
Past mannequin execution, LEAP positions itself as an all-in-one platform for locating, adapting, testing, and deploying SLMs for edge use.
Builders can browse a curated mannequin catalog with varied quantization and checkpoint choices, permitting them to tailor efficiency and reminiscence footprint to the constraints of the goal machine.
Liquid AI emphasizes that enormous fashions are typically generalists, whereas small fashions usually carry out finest when optimized for a slender set of duties. LEAP’s unified system is structured round that precept, providing instruments for fast iteration and deployment in real-world cellular environments.
The SDK additionally comes with a developer group hosted on Discord, the place Liquid AI presents workplace hours, help, occasions, and competitions to encourage experimentation and suggestions.
Apollo: like Testflight for native AI fashions
To enhance LEAP, Liquid AI additionally launched Apollo, a free iOS app that lets builders and customers work together with LEAP-compatible fashions in an area, offline setting.
Initially a separate cellular app startup that allowed customers to speak with LLMs privately on machine, which Liquid acquired earlier this 12 months, Apollo has been rebuilt to help the whole LEAP mannequin library.
Apollo is designed for low-friction experimentation — builders can “vibe verify” a mannequin’s tone, latency, or output conduct proper on their telephones earlier than integrating it right into a manufacturing app. The app runs completely offline, preserving consumer privateness and decreasing reliance on cloud compute.
Whether or not used as a light-weight dev instrument or a personal AI assistant, Apollo displays Liquid AI’s broader push to decentralize AI entry and execution.
Constructed on the again of the LFM2 mannequin household introduced final week
LEAP SDK launch builds on Liquid AI’s July 10 announcement of LFM2, its second-generation basis mannequin household designed particularly for on-device workloads.
LFM2 fashions are available in 350M, 700M, and 1.2B parameter sizes, and benchmark competitively with bigger fashions in velocity and accuracy throughout a number of analysis duties.
These fashions kind the spine of the LEAP mannequin library and are optimized for quick inference on CPUs, GPUs, and NPUs.
Free and prepared for devs to begin constructing
LEAP is at the moment free to make use of beneath a developer license that features the core SDK and mannequin library.
Liquid AI notes that premium enterprise options might be made obtainable beneath a separate business license sooner or later, however that it’s taking inquiries from enterprise clients already by way of its web site contact kind.
LFM2 fashions are additionally free for educational use and business use by firms with beneath $10 million in income, with bigger organizations required to contact the corporate for licensing.
Builders can get began by visiting the LEAP SDK web site, downloading Apollo from the App Retailer, or becoming a member of the Liquid AI developer group on Discord.
