Local first. Cloud when needed. Sync between.

I believe this will become one of the defining AI architecture principles of the coming years. It combines privacy, resilience, low latency and scalable intelligence.
#Qdrant #EdgeAI #AIInfrastructure #AISovereignt

🚀 Liquid AI lancia LFM2.5-230M, modello AI edge da 230M parametri

Il nuovo modello LFM2.5-230M di Liquid AI gira su smartphone e Raspberry Pi, battendo modelli 4x più grandi in data extraction. Disponibile open-weight per sviluppatori.

Fonte: Liquid AI

Segui 👇
#AI #EdgeAI #LiquidAI 🚀🤖🔥

Makerfabs MaTouch ESP32-P4 10.1-inch HMI display features 4G LTE and Ethernet connectivity, a 2MP camera

Makerfabs MaTouch ESP32-P4 TFTTouch 10.1 MIPI with 4G LTE is an ESP32-P4 + ESP32-C6-based display development platform for HMI edge AI, and connected embedded applications. The development board features a 10.1-inch IPS LCD, very similar to those of Seeed Studio’s reTerminal D1001, Waveshare ESP32-P4-WIFI6-Touch-LCD, and CrowPanel Advanced 7-inch displays. However, what makes it unique compared to other devices is that it also features a SIM7670G 4G LTE modem with a SIM card slot, an RJ45 Ethernet jack, and a 2MP camera. The HMI display also comes with microphone and speaker connectors, a microSD card slot, various USB interfaces, lithium battery support, and two 2.54 mm pitch GPIO expansion headers exposing UART, I2C, SPI, and other peripheral interfaces. All these features make it suitable for HMI, edge AI, and connected embedded applications. Makerfabs MaTouch ESP32-P4 10.1-inch 4G LTE specifications: SoC – Espressif Systems ESP32-P4NRW32 CPU Dual-core 32-bit RISC-V HP (High-performance) CPU @ up to 400

CNX Software - Embedded Systems News

🚨 NEWS: Liquid AI presenta il modello LFM2.5-230M per estrazione dati su dispositivi edge e robot

Ecco i punti chiave in breve:
💡 Liquid AI, fondata da ex ricercatori del MIT, ha rilasciato oggi il suo modello linguistico più compatto, denominato LFM2.5-230M. Con soli 230 milioni di parametri, questo modello...

🚀 LINK: https://meteoraweb.com/news/liquid-ai-presenta-il-modello-lfm25-230m-per-estrazione-dati-su-dispositivi-edge-e-robot?utm_source=mastodon&utm_medium=social&utm_campaign=auto_share

#robotUmanoide #liquidAI #lFM2.5230M #edgeAI #estrazioneDati

Firefly AIBOX-9075 Edge AI box features 200 TOPS Qualcomm IQ-9075 SoC, 36GB LPDDR5, industrial I/Os

The AIBOX-9075 is an industrial Edge AI box built around the Qualcomm IQ-9075 SoC, designed for running AI workloads directly on the device without relying on the cloud. With up to 200 TOPS of AI performance, it is designed for edge computing, private LLM deployment, robotics, computer vision, and more. The system comes with 36GB LPDDR5 ECC memory, 128GB UFS 2.2 storage, and an M.2 PCIe 4.0 NVMe SSD slot. Connectivity options include dual 2.5GbE with TSN, optional Wi-Fi 6, Bluetooth 5.2, and 4G/5G, while peripheral interfaces include eight GMSL2 camera inputs, HDMI 2.0, USB 3.0, CAN-FD, RS485, and opto-isolated digital I/O. Its rugged aluminum enclosure operates from -40°C to 85°C, making it suitable for continuous deployment in industrial and outdoor environments. Firefly AIBOX-9075 specifications: SoC – Qualcomm DragonWing IQ-9075 CPU Octa-core Kryo Gen 6 (Cortex-A78C-based) application cores @ up to 2.36 GHz Quad-core Cortex-R52 real-time cores @ up to 1.85GHz

CNX Software - Embedded Systems News
NeoEyes NE503 – A $1199 Edge AI Camera based on Hailo-15H 20 TOPS SoC

Camthink NeoEyes NE503 is a 4K Edge AI camera platform powered by the Hailo-15H quad-core Cortex-A53 SoC with a 20 TOPS AI accelerator, and paired with 8GB of LPDDR4 memory and a 64GB eMMC flash. The camera also features a Sony IMX678 4K sensor and an 8–32mm F1.6 AF auto-zoom lens for high-quality monitoring, low-light imaging, and long-range recognition. The camera directly handles high-resolution video input, local multi-model inference, containerized applications, and event-driven workflows on the device, without relying on the cloud or a local server. NeoEyes NE503 specifications: SoC - Hailo-15H CPU - Quad-core Arm Cortex-A53 @  1.3 GHz VPU - H.265/H.264 encoding ISP - Supports up to 12 MP resolution, 600 Mpixel/s pixel rate, HDR, and noise reduction AI performance - Up to 20 TOPS; < 50 ms target inference latency System Memory - 8GB LPDDR4 @ 4266 MT/s; 8.5 GB/s single-channel bandwidth Storage 64 GB eMMC flash 8

CNX Software - Embedded Systems News
Graperain GR1126MB development board features solder-on 3 TOPS Rockchip RV1126B AI Vision module

Graperain GR1126MB development board is based on a 42x42mm GR1126B 160-pin stamp-hole system-on-module powered by a Rockchip RV1126B AI camera SoC with a 3 TOPS NPU designed for AI vision, machine vision, and edge AI applications. Graperain GR1126 AI Vision system-on-module GR1126 specifications: SoC – Rockchip RV1126B CPU – Quad-core Arm Cortex-A53 up to 1.6 GHz with 32KB L1 I-Cache and 32KB L1 D-Cache, unified 512KB L2 Cache GPU – 2D Graphics Engine VPU Video Decoder – H.265/H.264 up to 4K @ 30 FPS Video Encoder  – H.265, H.264, JPEG up to 4K @ 45 FPS JPEG Decoder ISP - Built-in 12M ISP and 8M AI-ISP AI accelerator – Rockchip NPU engine up to 3 TOPS (INT8); supports INT4, INT8, INT16, and FP16 models; TensorFlow, ONNX, PyTorch, and Caffe frameworks. System Memory – 1GB or 2GB DDR3 by default, customizable up to 4GB LPDDR4/LPDDR4x Storage – 8GB, 16GB, 32GB, 64GB,

CNX Software - Embedded Systems News
TerraMaster F4-425 Pro 4+3 Hybrid NAS gets Intel Core 3 N350 or Core i3-N305 octa-core CPU

TerraMaster F4-425 Pro 4+3 Hybrid NAS  is an update of the F4-425 Plus Intel N150 NAS with a more powerful Intel Core 3 N350 "Twin Lake" octa-core processor or Core i3-N305 octa-core "Alder Lake-N" processor. Apart from the new processors, the new Pro model basically offers the same features with four SATA bays and three M.2 NVMe SSD sockets for storage (hence the 4+3 hybrid moniker), and dual 5GbE networking. It's equipped with 8GB or 16GB DDR5 memory, and also adds four USB 3.2 ports for peripheral expansion, and an HDMI port for terminal access. TerraMaster F4-425 Pro specifications: SoC (one or the other) Intel Core i3-N305 octa-core Alder Lake-N processor @ up to 3.8 GHz (Turbo) with 6MB cache, 32U Intel HD graphics @ 1,250 MHz; TDP: 15W Intel Core 3 N350 octa-core Twin Lake processor @ up to 3.9 GHz (Turbo) with 6MB cache, 32U Intel HD graphics

CNX Software - Embedded Systems News

Coin-cell powered Nordic nRF54L15 Tag prototyping platform supports Bluetooth Channel Sounding, Matter, Edge AI

https://fed.brid.gy/r/https://www.cnx-software.com/2026/06/23/nordic-nrf54l15-tag-prototyping-platform-supports-bluetooth-channel-sounding-matter-edge-ai/

Coin-cell powered Nordic nRF54L15 Tag prototyping platform supports Bluetooth Channel Sounding, Matter, Edge AI

Nordic Semiconductor has launched the nRF54L15 Tag, a tiny coin-cell-powered prototyping platform designed to accelerate the development of ultra-low-power wireless IoT devices, including asset trackers compatible with the Apple Find My and Google Find Hub ecosystems. Built around the company’s nRF54L15 wireless SoC, the 33 mm-diameter tag uses a 2.4 GHz radio and includes two on-board antennas to improve distance-measurement reliability with Bluetooth Channel Sounding. The platform also integrates a 6-axis IMU and an environmental sensor, which can be used in tracking, sensing, and basic edge processing applications. Nordic nRF54L15 Tag specifications: Wireless MCU – Nordic Semi nRF54L15 wireless SoC CPU Arm Cortex-M33 @ up to 128 MHz RISC-V coprocessor for “software-defined peripheral” Memory – 256 KB SRAM Storage – 1.5MB Non-volatile Memory (NVM) Wireless Bluetooth LE 6.0 (includes Channel Sounding) Thread, Zigbee (IEEE 802.15.4-2020) Matter Amazon Sidewalk Proprietary 2.4 GHz protocols with a new 4 Mbps mode NFC support Aliro (a

CNX Software - Embedded Systems News
MYiR MAC-B5760 fanless Edge AI industrial PC features Rockchip RK3576 SoC, optional RK1828 LLM/VLM module

MYiR MAC-B5760 is a fanless Edge AI industrial box PC powered by a Rockchip RK3576 SoC with a built-in 6 TOPs NPU, and equipped with 8GB LPDDR5 and 64GB flash by default. The embedded system offers two Gigabit Ethernet ports, four USB 3.0 ports, HDMI and mini DP video outputs, a 3.5mm audio jack, a USB-C port for convenient serial console access, an optional WiFi 6 and Bluetooth 5.4 module, and expansion capability through an M.2 socket for NVMe SSD or AI accelerator, and a mini PCIe socket to add 4G LTE/5G cellular connectivity. MYiR MAC-B5760 specifications: SoC – Rockchip RK3576 CPU 4x Cortex-A72 cores @ 2.2GHz, four Cortex-A53 cores @ 1.8GHz Arm Cortex-M0 MCU at 400MHz GPU – ARM Mali-G52 MC3 GPU with support for OpenGL ES 1.1, 2.0 and 3.2, OpenCL up to 2.0 and Vulkan 1.1 NPU – 6 TOPS (INT8) AI accelerator with support for INT4,

CNX Software - Embedded Systems News