NAS used to store your files in your local network for easy access, but new models like QNAP TS-216G, TS-AI642, and TS-133 feature an Arm processor (Rockchip RK3566 or RK3588) with a built-in NPU to accelerate image recognition, so that users can find their photos with a simple text search like “Disneyland Mickey Mouse”.
However, if you own an older NAS that lacks an AI accelerator, QNAP has launched the QAI-M100 (M.2 2280) and QAI-U100 (USB) equipped with a Rockchip RK1808 3 TOPS AI accelerator designed to speed up image and facial recognition by up to 36%.
QNAP QAI-M100/QAI-U100 specifications:
- SoC – Rockchip RK1808
- CPU – Dual-core Arm Cortex-A35 @ 1.6 GHz
- NPU – 3 TOPS NPU
- Memory – 1GB RAM
- Host interface
- QAI-M100 – M.2 2280 PCIe Gen2 x1 (M+B key) edge connector
- QAI-U100 – USB 3.2 Gen1 male port
- Accessories – Installation guide and heatsink (QAI-M100 only)
- Dimensions / Form factor
- QAI-M100 – M.2 2280 module
QAI-U100 – 92.5 x 29 x 11 mm USB stick
- QAI-M100 – M.2 2280 module
- Warranty – 1 year
Both AI accelerators are plug-and-play on QNAP NAS and automatically detected by the software, which also supports Google Coral Edge TPU and Hailo AI accelerators. The QAI-M100 requires a NAS with an M.2 2280 PCIe slot or a PCIe expansion slot to install a QNAP QM2 expansion card, while the QAI-U100 works with systems equipped with a USB 3.2 Gen 1 Type-A port.
Software requirements include QTS 5.2.1.2930 build 20241025 (or later) or QuTS hero h5.2.1.2929 build 20241025 (or later), and the accelerators work with QNAP AI Core v3.5.0+, Multimedia Console v2.7.0+, and QuMagie v1.5.1+.
QNAP Lab testing tested the QAI-M100 with the AMD Ryzen Embedded V1500B-powered TS-673A NAS and found out that the AI object recognition of QuMagie Smart Album was sped up by up to 36% and facial recognition by up to 22%. That does not seem like a lot, but maybe it will benefit some people.
You’d think a consumer company like QNAP would start selling its new QAI Edge AI accelerators as soon as they are announced, but neither is listed on the company’s online store or Amazon. Having said that, they are already available on QNAP Europe for 65.45 Euros (M.2) and 77.35 Euros (USB) respectively. No other company appears to be making M.2 RK1808 modules, but USB AI Compute sticks and mPCIe modules were made in the past, and the latter are still sold for close to $100. Additional information may be found on the product pages.
Thanks to TLS for the tip.
Jean-Luc started CNX Software in 2010 as a part-time endeavor, before quitting his job as a software engineering manager, and starting to write daily news, and reviews full time later in 2011.
Support CNX Software! Donate via cryptocurrencies, become a Patron on Patreon, or purchase goods on Amazon or Aliexpress. We also use affiliate links in articles to earn commissions if you make a purchase after clicking on those links.
