> **Source:** Core Electronics is an Australian maker-electronics retailer and manufacturer based in Newcastle, NSW, run by a team of makers and educators. We design and manufacture our own product lines (PiicoDev, CE originals) and are official retailers for iconic maker and industrial brands including Raspberry Pi, Arduino, Adafruit, SparkFun and DFRobot. Orders ship Australia-wide from our Newcastle warehouse. Prices are in AUD and include GST. Pricing, stock and dispatch on this page are generated from the store's live catalog. Full machine-readable index: https://core-electronics.com.au/llms.txt # Toybrick RK1808 AI USB Compute Stick for Deep Learning, up to 3 TOPs powered by Rockchip NPU **Type:** Product page · **SKU:** SS102991294 · **Brand:** [Seeed Studio](https://core-electronics.com.au/brands/seeed-studio-australia) **Page:** https://core-electronics.com.au/toybrick-rk1808-ai-usb-compute-stick-for-deep-learning-up-to-3-tops-powered-by-rockchip-npu.html ([markdown](https://core-electronics.com.au/toybrick-rk1808-ai-usb-compute-stick-for-deep-learning-up-to-3-tops-powered-by-rockchip-npu.html.md)) Description Toybrick RK1808 AI USB Compute Stick is a high-performance and low-power consumption USB accelerator designed for Deep Learning. It is... ## Pricing - **Price:** $229.95 (inc GST) — $209.05 AUD, exc GST - **Quantity discounts:** 5+ $200.68 (exc GST) · 10+ $194.41 (exc GST) ## Availability & dispatch - Out of stock — the product page offers email notification when it returns. ## How to buy - **Build a cart:** compose `https://core-electronics.com.au/cart/link?items=SS102991294:1` (comma-separated SKU:qty pairs) and share the link. Opening it shows a confirmation page with live pricing and stock before anything is added to the cart. - **Verify the cart first:** fetch `https://core-electronics.com.au/cart/link/SS102991294:1.md` for live line prices (inc & exc GST, quantity discounts applied), stock and dispatch estimates, and totals. Append `/to/{AU-postcode}` (or `/to/{country-code}:{postcode}`) before `.md` for delivery options and prices to that destination. Unknown, retired, or out-of-stock SKUs are flagged. (Query form `cart/link.md?items=...` also works but some robots parsers refuse query strings here.) - **Checkout** is completed on-site and includes a captcha at the payment step. Share the cart link; checkout takes it from there. - **Search the catalogue:** `https://core-electronics.com.au/search/{query}.md` (URL-encode the query; pages 2-3 at `search/{query}/{page}.md`; `search.md?q=` also works) - **Payment methods, purchase orders, policies and contact details:** https://core-electronics.com.au/llms.txt ## Description **Description** Toybrick RK1808 AI USB Compute Stick is a high-performance and low-power consumption USB accelerator designed for Deep Learning. It is equipped with Rockchip RK1808 Neural Processing Unit (NPU) features an accelerator delivering up to 3.0 TOPS and is coupled with two low-power Arm Cortex-A35 cores allowing it to run Linux. RK1808 AI USB computing stick can be used for AI inference, and also supports custom development for any specific AI application. How is the performance? So that’s roughly equivalent to the *Intel*® *Movidius*™ Myriad™ *X* said 4 TOPs. The stick also comes with 1GB of LPDDR memory, and onboard 8GB of EMMC storage when you connect to a host computer. **Features** - **Powerful AI computing power:** built-in RK1808 NPU up to 3 TOPS, dual-core Cortex-A35 architecture. - **Strong compatibility:** host server supports Windows, Linux, macOS, and Arm Linux. - **Prepare for AI developers**: [RKNN toolkit](https://github.com/rockchip-linux/rknn-toolkit) offers development support in both C++ and Python. Model conversion supports mainstream frameworks including PyTorch, TensorFlow,Caffe, MXNet - **Scalability:** supports multiple stick overlays on the same platform to increase host performance. - **Built-in storage,** use as a USB disk with the documentation and software tools stored on the stick itself. **Work as an AI accelerator** You’ll need to install the RK1808 compute stick on another Ubuntu 16.04/x86\_64 PC if you want to convert your models to use on the Arm device like Raspberry Pi. RKNN-Toolkit is an SDK for model conversion, inference, and performance evaluation The host computer transmits the model and pre-processed data to the RK1808 artificial intelligence computing stick through RKNN-Toolkit, and the RK1808 artificial intelligence computing stick completes the inference and returns the results to the host computer, and the host computer performs post-processing and display operations. The following platforms and systems are supported as host machines: - At least Ubuntu 16.04/x86\_64 PC or higher, Windows, Mac OS - RK3399, RK3399Pro, Android system ![](https://core-electronics.com.au/attachments/localcontent/RK1808_passive_flow_265559f726e.png) The overall data flow diagram is as follows: ![](https://core-electronics.com.au/attachments/localcontent/RK1808_passive_flow_2_35024682150.png)**Connecting the RK1808 USB Stick to a Host Computer** The [rknn-toolkit](https://github.com/rockchip-linux/rknn-toolkit) is already installed inside the RK1808 AI computing stick by default. The host computer does not need to install rknn-toolkit and rknn-api. The host computer only needs to connect to the computing stick through the USB port. Input data (such as images and video streams), the RK1808 artificial intelligence computing stick automatically completes the pre-processing, inference, and post-processing of the data, and then outputs the processing results to the host computer through the USB port. The host computer here can be any platform with a USB interface and any operating system, including X86/X64/Arm32/Arm64, Linux/Windows/Mac OS and Raspberry Pi, etc… ![](https://core-electronics.com.au/attachments/localcontent/RK1808_Avtive_dev_38442f147ec.png)![](https://core-electronics.com.au/attachments/localcontent/RK1808_active_2_3494401278e.png)**Specifications** | CPU | RK1808 | |---|---| | Memory | 1GB LPDDR | | Storage | 8GB EMMC | | Size | 82×31×13mm | | Interface | USB3.0 Type-A | | Mini-system requirement | Ubuntu 16.04 or x86\_64 PCCPU intel core i3USB 3.02 GB RAM4 GB Storage | | Temperature | 0°C ~ 40°C | #### Documentations [RK1808 AI Compute Stick Datasheet](https://core-electronics.com.au/attachments/localcontent/RK1808_AI_Compute_Stick_User_manual_EN_296228c300d.pdf) ## Images - [Product image 1](https://core-electronics.com.au/media/catalog/product/S/S/SS102991294-1.jpg)