Scale Mobile AI without Scaling Cost or Complexity

Discover how Phison and MediaTek are rethinking memory architecture to unlock next-generation AI on smartphones.

Smartphones are becoming a primary platform for AI. What began with basic on-device features has quickly evolved into support for large language models, multimodal applications, and always-on experiences that run closer to the user.

Running AI locally improves responsiveness, reduces reliance on cloud infrastructure, and keeps sensitive data on the device. It also enables real-time, persistent interactions that are difficult to deliver through cloud-based models alone.

Mobile AI is a defining platform shift

AI is moving to where data is created, and that increasingly means the smartphone. Devices are no longer just endpoints for AI output. They are becoming environments where models run and respond in real time.

This shift is driven by three pressures: the need for low latency, greater control over data, and the rising cost of cloud-based inference at scale. Local AI addresses all three by delivering faster performance, keeping data on-device, and reducing dependence on external services.

The result is a new class of always-on, context-aware experiences that operate continuously in the background. The opportunity is clear, but there is still a gap between what mobile AI promises and what today’s hardware can consistently deliver.

The constraints holding mobile generative AI back

Generative AI is inherently memory-intensive. Running AI models requires significant resources to store parameters, manage tokens, and maintain context during inference. On smartphones, those requirements quickly come up against real-world limitations.

Today’s most common approaches to AI training and inference, whether on a smartphone or in the cloud, present challenges on multiple fronts:

• • • Cloud-based AI introduces concerns around privacy, security, and ongoing token costs
    • Dependence on connectivity creates latency and availability issues
    • On-device approaches struggle with limited memory capacity and the high cost of scaling DRAM
    • Slow response times can degrade the user experience

These constraints create a difficult tradeoff. Users can either rely on the cloud and accept its limitations or attempt on-device AI and run into performance and cost barriers.

To move forward, the industry needs a different approach to how memory is used in mobile systems.

A new approach to mobile AI architecture

Recently, Phison and MediaTek partnered to address this challenge with a fundamentally different way of thinking about memory.

The joint solution combines the MediaTek Dimensity 9500 SoC with Phison’s Pascari aiDAPTIV™ solution, introducing a new AI inference architecture for smartphones that extends beyond DRAM limitations.

At a high level, the approach is simple but powerful, as it:

• • • Extends the memory hierarchy by incorporating NAND flash alongside DRAM
    • Uses intelligent middleware to dynamically manage data across memory tiers
    • Treats memory and storage as a unified, coordinated resource

Instead of relying solely on DRAM, aiDAPTIV leverages NAND flash as an extension of working memory, significantly expanding the available memory pool for AI workloads.

The key enabler is the aiDAPTIV Memory Management Middleware, which acts as a coordination layer between the SoC, DRAM, and UFS storage. It dynamically streams model data where it’s needed, effectively breaking the boundary between memory and storage.

This creates a hybrid architecture where frequently accessed AI data is cached intelligently, storage is partitioned into dedicated regions for system data and AI workloads, and data can be reused and offloaded dynamically to optimize performance.

In practical terms, this means your smartphone can handle larger models, longer contexts, and more complex inference tasks without requiring a dramatic increase in DRAM.

Turn memory from a constraint into an advantage with Phison and MediaTek

This architectural shift delivers measurable benefits that directly address the core challenges of mobile AI.

Reduced DRAM requirements
Typical mobile AI deployments may require 16 GB or more of DRAM to support advanced models or use cases, such as when leveraging mixture of experts (MoE). With dynamic model and MoE offloading and intelligent memory management, the aiDAPTIV approach can reduce those requirements to around 12 GB while maintaining performance.

Lower system cost and improved efficiency
By leveraging the cost advantages of NAND flash, the Phison-MediaTek solution reduces the need for expensive DRAM scaling. This enables more cost-effective device designs without sacrificing AI capability.

Support for larger models and longer context windows
The expanded memory pool allows your smartphone to handle more complex models and longer sequences, unlocking richer and more capable AI experiences.

Improved privacy and autonomy
Running inference locally reduces dependence on cloud infrastructure, helping protect sensitive data and enabling AI functionality even without connectivity.

Building the foundation for next-generation mobile AI

Part of what makes this collaboration so significant is the performance gains, but it’s also about the shift in how smartphone systems are designed to support AI.

By unifying memory and storage into a coordinated architecture, Phison and MediaTek are enabling a new class of smartphones that can:

• • • Run advanced AI models locally
    • Deliver faster, more responsive user experiences
    • Balance performance, cost, and power efficiency
    • Scale AI capabilities without scaling hardware complexity

This is a foundational step toward truly autonomous, always-on AI at the edge.

Looking ahead

As mobile AI continues to evolve, memory will remain one of the most important factors shaping what is possible. Solutions that rethink how memory is structured and utilized will define the next wave of innovation.

The collaboration between Phison and MediaTek represents a clear direction forward. By transforming memory from a bottleneck into a scalable resource, it opens the door to more capable, efficient, and accessible AI experiences on the smartphone.