Atomiq

Ambitious Edge AI

The Atomiq® SoC enables a new class of always-on edge AI through SPOT®, delivering high-performance NPU workloads with unmatched power efficiency for advanced audio, language, vision, and reasoning.

High Performance Meets Power Efficiency

01

AI in Overdrive

Atomiq leverages the Arm® Ethos™-U85 NPU to deliver over 200 GOPS of on-device AI performance, with support for sparsity and on-the-fly weight decompression to accelerate complex workloads.

02

Dynamic Power Scaling

SPOT-based ultra-wide range dynamic voltage and frequency scaling (DVFS) enables operation at lower voltages and power than previously possible, making advanced, always-on edge AI practical.

03

Robust Software

Ambiq’s helia™ AI platform, ADKs, and neuralSPOT® SDK deliver a tightly integrated hardware-software stack that enables high performance, lower memory footprint, ultra-low power, and significantly faster AI deployment.

04

Leading Energy-Efficiency

The SPOT platform brings breakthrough ultra-low-power efficiency, dramatically reducing energy consumption for next-generation edge workloads.

12nm SPOT Platform

TSMC 12nm FinFET Node

  • Atomiq is built on TSMC's 12nm FinFET node, which, when combined with the SPOT platform, enables high-speed sub- and near-threshold operation that was previously impractical in earlier planar nodes.

Power Levels as Low as 300mV

  • The new Ultra-Low Power (ULP) mode is engineered to operate close to 300mV while maintaining practical performance levels, expanding Atomiq's dynamic range across ULP, Low-Power (LP), and High-Performance (HP) modes.

Multi-Channel SIMO Buck Converter

  • Featuring a multi-channel Single-Inductor Multiple-Output (SIMO) buck converter that adapts across processes, temperatures, and workloads, delivering 6 different voltage rails at loads ranging from nanoamps to milliamps.

Purpose-Built for Edge AI

  • By performing hundreds of multiply-accumulate (MAC) operations in parallel, Atomiq achieves tens of billions of operations per second at clock speeds as low as 100 MHz, enabling edge devices to process complex AI models on-device both quickly and energy-efficiently.

Subscribe for the Latest News About Atomiq

    FAQ

    • Atomiq is Ambiq’s next-generation SoC architecture integrating an NPU, designed to enable scalable, ultra-low-power AI at the edge. It’s built on our patented SPOT® platform and represents a major milestone in how we architect future always-on AI systems.

    • No. This is a platform milestone announcement, not a commercial product launch. Atomiq is not yet available for customer deployment, and we’re not demonstrating Atomiq silicon at CES. This announcement provides early visibility into our architectural direction and long-term roadmap.

    • CES is where customers, partners, and investors look for directional signals, not just products. Atomiq reflects years of internal development and customer engagement, and announcing it now helps align the ecosystem around where edge AI is heading—and where Ambiq is investing.

    • Apollo is the foundation of Ambiq’s current edge AI success. Atomiq extends that foundation, introducing a new system architecture optimized for higher-performance, always-on AI workloads as models grow larger and more complex.
      A simple way to think about it:
      Apollo powers today’s edge AI deployments; Atomiq defines the next phase.

    • Absolutely. Apollo remains central to our portfolio and revenue today. Atomiq builds on Apollo’s success—it doesn’t replace it.

    • Atomiq introduces a system-level architecture designed from the ground up for AI workloads, including a dedicated NPU, while retaining Ambiq’s leadership in ultra-low-power operation through SPOT®. It’s about scaling intelligence without scaling power.

    • Ethos-U85 provides meaningful gains in AI performance and efficiency, and it aligns well with our SPOT® platform. Together, they enable larger models and more complex workloads at power levels that weren’t previously practical at the edge.

    • Applications that demand always-on intelligence, such as:

      • Conversational AR glasses
      • Advanced wearables
      • Smart cameras

    • They represent two ends of the edge AI spectrum—ultra-compact consumer devices and mission-critical industrial systems. Together, they show how Ambiq’s platforms scale across vastly different constraints and use cases.

    • We haven’t announced availability timelines. We plan to share additional technical details and roadmap updates beginning in March 2026 at Embedded World.

    • It represents the next step in pushing voltage, power efficiency, and memory architecture even further—enabling more advanced AI at lower energy budgets

    • The new Ultra-Low Power (ULP) mode allows Atomiq to operate at voltages as low as 300 millivolts (mV) while still maintaining meaningful processing performance.
      This enables developers to run Intensive AI workloads using significantly less energy than traditional operating modes, delivering one of Ambiq’s most energy efficient and powerful SoCs to date.

    • Atomiq combines several innovations, including:

      • Ambiq’s Subthreshold Power Optimized Technology (SPOT) design methodology
      • TSMC’s 12nm FinFET N12e process
      • A redesigned power management unit
      • A multi-channel Single-Inductor Multiple-Output (SIMO) buck converter
      • New custom foundation IP optimized for ultra-low-voltage operation
      Together, these technologies allow reliable operation at extremely low voltages while maintaining performance.

    • Even at ultra-low voltages and clock speeds around 100 MHz, Atomiq’s AI accelerator can deliver tens of billions of operations per second, thanks to parallel processing.

    • Atomiq supports three power-performance modes:

      • ULP (Ultra-Low Power) – lowest voltage and energy consumption
      • LP (Low Power) – balanced efficiency and performance
      • HP (High Performance) – maximum compute capability
      This wide dynamic range allows devices to scale performance based on workload demands.

    • Atomiq includes a highly configurable multi-channel SIMO buck converter, which uses a single inductor to power multiple voltage rails.
      This design improves efficiency while enabling six independent voltage rails that can dynamically adjust to:

      • Workload requirements
      • Temperature variations
      • Process variations
      The system can support load ranges from nanoamps to milliamps, helping maintain efficiency across a wide operating range.

    • Yes. The 12nm SPOT platform has been validated on silicon in Ambiq’s laboratories, representing an important milestone toward production of the Atomiq series, starting with the Atomiq110 SoC in 2027.

    Preparing to download