World Congress 2026 Europe Jul 10, 2026 Session details

Edge AI on iOS: Beyond the Cloud, Designing the Next Generation of Intelligent On-Device Apps

Precious Osaro

Why rely on expensive cloud APIs when modern iOS hardware can run 3-billion-parameter models natively? Master 2-bit quantization and agentic architecture to build lightning-fast, offline AI apps.

Pause
Mute Enter Fullscreen
#1 about 4 min

Reducing cloud dependency with on-device edge AI models

How rising API costs and capable mobile hardware are driving the adoption of edge AI.

#2 about 3 min

Understanding model quantization for efficient on-device processing

Applying multi-bit quantization to shrink massive parameter models into small memory footprints without losing context accuracy.

#3 about 2 min

Using key-value caching to accelerate local token generation

Using key-value caching to reduce computational complexity and accelerate first token generation speeds.

#4 about 1 min

Navigating Apple's evolving on-device AI and machine learning stack

Navigating Apple's current AI tooling and adapting to dynamic profiles and deprecated features post-WWDC.

#5 about 3 min

Solving indoor navigation with local vision-language models

Replacing hardware beacons with a local vision-language model combined with pre-defined node graphs to route users indoors.

#6 about 3 min

Designing an agentic intent architecture for AI interactions

Creating an intent-driven framework that bridges user inputs and large language model execution.

#7 about 3 min

Applying dynamic profiles and guided generation techniques

Configuring model profiles and enforcing structured JSON responses dynamically to integrate with strictly typed Swift code.

#8 about 4 min

Demonstrating on-device indoor navigation in real time

A practical walkthrough of real-time route-finding using device cameras and local mapping models without cloud connectivity.

#9 about 2 min

Managing token windows and memory constraints in production

Implementing rolling windows and discarding unnecessary tool-call history to stay within tight device memory limits.

#10 about 2 min

Unit testing and dataset generation for probabilistic AI

Validating dynamic model responses with frameworks and leveraging private cloud compute to generate comprehensive test datasets.

#11 about 2 min

Optimizing response latency and tracking resource consumption

Improving user experience through pre-warming approaches while carefully instrumenting heat, power, and memory utilization limits.

#12 about 3 min

Building OS-level model registries for flexible edge AI

A forward-looking proposal for a system registry where mobile applications dynamically request specific open-source AI models.

#13 about 2 min

Addressing mobile energy limits and AI processing tradeoffs

Discussing strategies like minimizing context windows to mitigate severe battery and thermal drain from continuous processing.

Matching moments

4:12 min

Shifting from AI features to AI-assisted iOS development

MIlan Todorović MIlan Todorović · World Congress 2026 Europe

3:38 min

The convergence of mobile engineering and machine learning

Sasha Denisov Sasha Denisov · World Congress 2026 Europe

7:00 min

Evaluating on-device data privacy, model performance, and cross-platform alternatives

Milan Todorovic · World Congress 2021

48 sec

Shifting artificial intelligence models to local smartphone hardware

Chris Heilmann +1 · LIVE

1:45 min

Transitioning from API consumers to on-device AI builders

Sasha Denisov Sasha Denisov · World Congress 2026 Europe

1:15 min

Debunking common biases about limited mobile AI capabilities

Sasha Denisov Sasha Denisov · World Congress 2026 Europe

Upcoming sessions on this topic

Open session

World Congress 2026 North America

September 24, 2026 · 14:10–14:40

Stage 5

Edge AI: Running Agentic Intelligence Where Internet Can't Reach

Nitin Eusebius

AWS - Principal Solutions Architect

Nitin Eusebius
Open session

World Congress 2026 North America

September 25, 2026 · 13:30–14:00

Stage 1

The State of Local AI in 2026

Kirah Sapong

Co-founder & CTO of Aquaduck AI

Kirah Sapong
Open session

World Congress 2026 North America

September 24, 2026 · 16:10–16:40

Stage 5

From Software Agents to Physical Devices: Inside the Agentic Hardware Stack

Michael Yuan, Vivian Hu

Michael Yuan
Vivian Hu
Open session

World Congress 2026 North America

September 25, 2026 · 14:50–15:20

Stage 4

Intelligence in Motion: Building the Next Generation of AI-Powered Apps on Zoom's Developer Platform

Brendan Ittelson

Chief Ecosystem Officer of Zoom

Brendan Ittelson
Open session

World Congress 2026 North America

September 24, 2026 · 14:10–14:40

Stage 7

Designing High-Performance AI APIs: Lessons from Serving Millions of Real-Time Requests

Wayne Liu

Chief Growth Officer and Americas President of Perfect Corp.

Wayne Liu
Open session

World Congress 2026 North America

September 23, 2026 · 10:00–17:00

Stage 11

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben