Ultra-low-power wireless SoC
with integrated Axon NPU
The nRF54LM20B is an ultra-low-power wireless SoC from Nordic’s nRF54L Series, integrating an efficient MCU, Axon NPU, and multi-protocol connectivity (Bluetooth LE/Mesh, Matter, Thread, etc.). It boasts the series’ largest memory (2MB NVM, 512KB RAM), up to 66 GPIOs, and high-speed USB. With 503 CoreMark performance, 15x faster on-device AI inference, ultra-low power (0.7–4.0μA sleep, 3.4mA RX), and robust security, it reduces design complexity, extends battery life, and enables reliable edge AIoT applications.
The nRF54L Series offers SoCs that combine an efficient MCU with ultra-low-power wireless connectivity. The nRF54LM20B provides the largest memory option in the series, with 2 MB NVM and 512 KB RAM. It features an extended set of peripherals, high-speed USB, and is available with up to 66 GPIOs.
The nRF54LM20B also includes an integrated Axon NPU, increasing the speed and efficiency of on-device AI inferencing up to 15x compared to using he CPU for the same task.
nRF54LM20B supports Bluetooth LE, Matter, Thread, Zigbee, and 2.4 GHz proprietary protocols with data rates up to 4 Mbps for low-latency applications. It also supports Bluetooth Channel Sounding, Bluetooth Mesh, and Wi-Fi with nRF70 Series companion ICs.
Features
- Processing efficiency and performance: 193 CoreMark/mA @ 3 V, 503 CoreMark®
- Enhanced edge AI capabilities thanks to integrated Axon NPU
- Radio power consumption: 3.4 mA for RX and 4.8 mA for TX @ 0 dBm (@ 3 V)
- Sleep modes power consumption: from 0.7 μA to 4.0 μA (@ 3 V)
- Maximum TX power: +8 dBm (CSP) / +7 dBm (QFN)
- Sensitivity: -96 dBm (1M Bluetooth LE), -101 dBm (802.15.4)
- Optimized for the lowest total average current
Application
- Increased speed and efficiency of AI inference tasks
- Reduced design complexity, size, and cost
- Reliable and robust wireless connectivity
- Extended battery life enabled by lower power consumption
- Built-in security features supporting compliance with regulations
- Broad range of MCU feature sets across the series
