WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 10, 2026 • Session details

Future of Mobile AI. What On-Device Intelligence Means for App Developers

Sasha Denisov

Stop paying exorbitant cloud API fees for mobile AI. Learn how modern NPUs and on-device models let you build zero-latency, offline-first applications with complete data privacy.

Pause
Mute Enter Fullscreen
#1 about 2 min

Evolution of AI into the agentic era

The AI landscape is progressing from predictive machine learning to generative models and autonomous agents.

#2 about 4 min

Technological shifts enabling practical edge AI deployment

Smaller models, capable hardware, and optimized runtimes make offline on-device inference a practical reality.

#3 about 1 min

Advantages of edge inference over cloud API services

On-device models offer improved privacy, zero cloud costs, offline availability, and minimal network latency.

#4 about 2 min

Debunking common biases about limited mobile AI capabilities

Modern mobile devices can run complex generative language models instead of being restricted to narrow machine learning tasks.

#5 about 4 min

Utilizing open models for customized mobile integration

Open-weight models like the Gemma family allow developers to process private data and fine-tune systems for specific application requirements.

#6 about 4 min

Selecting runtimes and frameworks for on-device inference

Efficient runtimes and mobile frameworks connect raw model formats to device hardware architecture for optimal local execution.

#7 about 4 min

Implementing hybrid routing between local and cloud models

Architectural routing patterns delegate inference tasks based on computational complexity, privacy needs, and network connectivity.

#8 about 4 min

The convergence of mobile engineering and machine learning

Developing robust on-device intelligence requires combining traditional application lifecycle management with model inference expertise.

#9 about 2 min

Transitioning from API consumers to on-device AI builders

Developers must adopt local processing models to ensure strict user privacy and escape escalating cloud computational fees.

#10 about 1 min

Handling hardware capability variations across user devices

Mobile applications should dynamically check hardware constraints and fall back to cloud alternatives for unsupported legacy devices.

#11 about 2 min

Managing operational costs for local model deployments

Executing models locally consumes device battery power rather than generating recurring per-token utility expenses for the user.

Matching moments

3:21 min

Reducing cloud dependency with on-device edge AI models

Precious Osaro Precious Osaro · World Congress 2026 Europe

48 sec

Shifting artificial intelligence models to local smartphone hardware

Chris Heilmann Chris Heilmann +1 · LIVE

2:26 min

Cost and latency pressures pushing AI to the edge

Moe Sani Moe Sani · World Congress 2026 Europe

51 sec

Adopting hybrid approaches for browser-based AI models

Jason Mayes · Coffee With Developers

2:12 min

Distilling cloud AI capabilities into local device models

1:41 min

Addressing mobile energy limits and AI processing tradeoffs

Precious Osaro Precious Osaro · World Congress 2026 Europe

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
3 months ago

Building the Nervous System of AI - Michael Kagan (NVIDIA)

Michael Kagan, Sead Ahmetović

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote thumbnail
19:41
3 months ago

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote

Christian Heilmann

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend thumbnail
32:06
3 months ago

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

David vonThenen

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes thumbnail
35:13
3 months ago

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes

Irina Branovic

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬 thumbnail
24:23
3 months ago

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬

Jeremy Murray

Angstfreude - AI and Corporate Culture - The Thrill and the Threat thumbnail
30:26
3 months ago

Angstfreude - AI and Corporate Culture - The Thrill and the Threat

Axel Ebert, Karin Krobath

Related videos

Edge AI on iOS: Beyond the Cloud, Designing the Next Generation of Intelligent On-Device Apps thumbnail
26:30
World Congress 2026 Europe • 3 months ago

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

Precious Osaro

Google Gemma and Open Source AI Models - Clement Farabet thumbnail
47:25
over 1 year ago

Google Gemma and Open Source AI Models - Clement Farabet

Mobile AI Just Got Faster: What’s Coming for Developers on Arm thumbnail
23:09
World Congress 2025 • about 1 year ago

Mobile AI Just Got Faster: What’s Coming for Developers on Arm

Gian Marco Iodice

The Retrieval Layer for Edge AI thumbnail
28:37
World Congress 2026 Europe • 3 months ago

The Retrieval Layer for Edge AI

Sasha Denisov, Chadha Sridi

AI in Your Browser: Exploring Chrome's Built-In LLM thumbnail
29:59
World Congress 2026 Europe • 3 months ago

AI in Your Browser: Exploring Chrome's Built-In LLM

Daniel Ostrovsky

RTX AI PC: Developing local and edge AI applications thumbnail
26:06
World Congress 2026 Europe • 3 months ago

RTX AI PC: Developing local and edge AI applications

Joerg Krall

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.