| |
Ambiq Micro, Inc. (“Ambiq®”), a technology leader in ultra-low power semiconductor solutions for edge AI, today announced the release to market (RTM) of its Apollo330 Plus and Apollo510 Lite SoC series. The six products, designed to help manufacturers bring high-performance, power-efficient edge AI devices to market faster, are now available.
The Apollo330 Plus and Apollo510 Lite series span six variants Apollo330 Plus, Apollo330B Plus, Apollo330M Plus, Apollo510 Lite, Apollo510B Lite, and Apollo510D Lite offering flexible connectivity and graphics options for a broad range of applications, including wearables, hearables, AR devices, digital health monitors, and industrial sensors.
With over 16x higher performance1, lower latency, and up to 30x better AI energy efficiency2 than previous-generation Cortex-M-based solutions, the series enables always-on, responsive, on-device intelligence without relying on cloud compute extending battery life and improving the user experience.
Key Features:
• 48/96 MHz Arm® Cortex-M4F network processor with multi-protocol radio (wireless variants);
• Up to 16x faster performance and lower latency, with up to 30x better AI energy efficiency compared to previous-generation Cortex-M-based processors;
• 2D/2.5D GPU, vector graphics acceleration, and Ambiq’s graphiqSPOT® for crisp, high-quality displays at ultra-low power (Apollo510 Lite Series);
• Ultra-low-power PDM interface enabling truly always-on voice capabilities;
• Connectivity support for Bluetooth® Low Energy, Bluetooth Classic, LE Audio, and Auracast™ (Apollo330M Plus);
• Matter and Thread support via Apollo330M Plus (planned for future OTA update);
• Multiple packages, including BGA and WLCSP.
Designed for Intelligent, Battery-Powered Devices
The Apollo330 Plus and Apollo510 Lite series are built on Ambiq’s proprietary Subthreshold Power Optimized Technology (SPOT®) platform and powered by the Arm® Cortex®-M55 with Helium™ technology, delivering high-performance AI processing with ultra-low power consumption for always-on edge devices.
The series integrates efficient AI acceleration (up to 8 MACs per cycle), up to 2MB SRAM and 2MB embedded NVM, and large instruction and data caches enabling responsive, power-efficient edge intelligence across a wide range of applications. A streamlined multi-core architecture separates application and network processing, ensuring robust wireless performance (up to +13 dBm TX output) while maintaining ultra-low power consumption.
Security is built in with Ambiq secureSPOT® 3.0, leveraging Arm TrustZone® technology designed to support secure boot, secure firmware updates, and hardware-based protection of sensitive data.
Availability
The Apollo330 Plus and Apollo510 Lite series are available now through Ambiq’s eStore and authorized distributors.
About Ambiq
Ambiq’s mission (ambiq.com) is to enable intelligence (artificial intelligence (AI) and beyond) everywhere by delivering the lowest power semiconductor solutions. Built on its patented Subthreshold Power Optimized Technology (SPOT®) and the HELIA™ AI platform, Ambiq empowers manufacturers to bring more capable AI to the edge, where power, memory, and energy efficiency are most critical. Ambiq enables more intelligent, always-on edge devices across healthcare, wearables, industrial automation, smart environments, and other emerging AI applications. With more than 300 million devices shipped worldwide, Ambiq continues to shape the future of always-on Edge AI. Headquartered in Austin, Texas, Ambiq serves customers globally.
Ambiq Micro and the Ambiq logo are registered trademarks of Ambiq Micro, Inc. All other company or product names noted herein may be trademarks of their respective holders.
Teneo Investor Relations Contact: Christina Coronios
E: christina.coronios[.]teneo.com.
1. Based on Arm Cortex-M55 vs. Cortex-M4 performance data. Performance improvement varies by data type; up to 16x for 16-bit floating point operations. Source: Arm Cortex-M55 Product Brief
2. Based on Ambiq internal testing. Energy efficiency improvement of up to 30x compared to typical Cortex-M4 and Cortex-M33 MCUs running AI workloads. Results may vary depending on application and configuration.
|
cwan[.]ambiq.com 
