Rockchip RK1828 AI Acceleration Module for Edge AI (M.2 Module, 20 TOPS)

SKU: DF-DFR1263
Sale price A$553.15   Inc. GST
11 units ships in 7 to 10 days

This RK1828 AI accelerator is a high-performance AI coprocessor designed to add local AI inference capability to edge computing systems. Built on the Rockchip RK1828 platform, this M.2 AI accelerator integrates a 20 TOPS NPU with 5 GB of high-bandwidth DRAM, providing dedicated acceleration for large language models, multimodal models, speech processing and computer vision workloads in robotics, industrial systems, smart terminals and edge servers.

Rockchip RK1828 AI Acceleration Module for Edge AI (M.2 Module, 20 TOPS)

20 TOPS Compute with 1 TB/s Memory Bandwidth

This edge AI accelerator delivers 20 TOPS of NPU performance at INT8 and supports INT4, INT8, INT16, FP8, FP16 and BF16 precision formats. The integrated 5 GB DRAM provides 1 TB/s bandwidth, reducing memory-access bottlenecks during model inference. Under the specified test conditions, Qwen3-8B reaches 61.34 decode tokens per second, while Qwen3-4B reaches 88.47 tokens per second, enabling responsive local large-model inference for AI assistants and human-machine interaction.


One Accelerator for LLM, VLM, Speech and Vision Workloads

This RK1828 NPU supports more than 20 mainstream models across LLM, VLM, retrieval, ASR, TTS and computer vision categories. Supported examples include Qwen3-8B, Qwen2.5-VL-7B, Qwen2.5-Omni-3B, InternVL3.5-4B, Whisper, Qwen3-ASR, Qwen3-TTS, YOLOv8s and DINOv3. Pre-converted RKNN models and sample code reduce the amount of model conversion and deployment work required for proof-of-concept development.


RKNN3 Toolchain for Model Conversion, Deployment and Benchmarking

This AI coprocessor works with the RKNN3 software stack for model conversion, inference execution, performance evaluation and board-side deployment. Support for frameworks including TensorFlow, Caffe, TFLite, PyTorch, ONNX NN and Android NN provides a practical path from existing AI models to hardware-accelerated edge deployment.


Standard M.2 Form Factor for Edge System Integration

This M.2 AI accelerator uses a B-M Key interface and communicates through PCIe 2.1 ×1 Lane. The module follows the M.2 2280 form factor and uses an external DC 12 V power input, reducing the power demand placed on the host M.2 slot. Android, Linux and Windows compatibility allows integration with x86 or ARM hosts, industrial PCs and compatible development boards.


With dedicated AI compute, high-bandwidth memory and support for multiple AI model categories, this RK1828 AI accelerator is suitable for upgrading edge platforms that require local inference. Typical deployments include home computing hubs, industrial defect inspection, robot control systems, security surveillance and meeting transcription systems.

Features:

  • 20 TOPS NPU computing performance at INT8
  • 5 GB integrated DRAM with 1 TB/s memory bandwidth
  • Qwen3-8B decode performance of 61.34 tokens/s under specified test conditions
  • Supports INT4 / INT8 / INT16 / FP8 / FP16 / BF16 precision formats
  • Supports LLM, VLM, retrieval, ASR, TTS, image feature, classification and object detection models
  • RKNN3 toolchain supports model conversion, inference, benchmarking and deployment
  • M.2 B-M Key interface with PCIe 2.1 ×1 Lane communication
  • Compatible with Android, Linux and Windows systems
  • External DC 12 V power input reduces power demand on the host M.2 slot
  • Applications:

  • Home computing hubs
  • Industrial defect inspection
  • Robot control cores
  • Security surveillance
  • Meeting transcription systems
  • Specification:

    Basic Parameters

  • VCC_IN Input: DC 12 V
  • Power Consumption:
         Average: 13.6 W
         Peak: 29.4 W (under 7B model workload)
  • Hardware Interface: M.2 B-M Key
  • Communication Bus: PCIe 2.1 ×1 Lane
  • NPU Compute Performance: 20 TOPS @ INT8
  • Supported Precision Formats: INT4 / INT8 / INT16 / FP8 / FP16 / BF16
  • Supported Frameworks: TensorFlow, Caffe, TFLite, PyTorch, ONNX NN, Android NN, etc.
  • DRAM Configuration: 5 GB, 1 TB/s bandwidth
  • Physical Dimensions

  • Dimensions: 25 × 81 × 21.75 mm (heat sink included)
  • Product Includes:

  • RK1828 AI Accelerator (M.2 Module) x1
  • Single-head GH1.23-4P 15 cm Cable x1
  • Shipping rates Australia wide and New Zealand

    Please add the items in cart and proceed to checkout to calculate shipping cost. We have range of shipping options once goods are ready to dispatch. 
    1. Regular shipping: Goods will be shipped using Australia post regular shipping service. 
    2. Express shipping: Goods will be shipped using Australia post EXPRESS shipping service. 
    3. Express split shipping: Local stock from Melbourne will be shipped ASAP (1 business day) using EXPRESS shipment while remaining items from overseas stock when arrived in Melbourne shipped using second EXPRESS shipment. 
    4. Pick up from Thomastown, Melbourne is available on appointment between 9 am to 3 pm during business days. 

      

    FAQ:

    • How do I estimate shipping for my order?
      • Add products in the shopping cart and head to the checkout page to estimate the shipping.

    Dispatch time

    Unless expressly agreed otherwise with you, we will not commence delivery of an order until we have received cleared payment of the purchase price in full.

    All orders placed before 11 am AEST (Monday to Friday) will ordinarily be processed on the same day.

    We will endeavour to ship the Products by the applicable time indicated on the website, but all times are indicative only.  All shipping times are dispatch times only, and actual delivery dates will depend on the shipping method chosen, delivery address and delivery service provider. 

    Note- Please make a note during purchase if you require any item urgently. However we cannot guarantee that we will be able to comply with any request. 

    *Go to Australia post delivery time calculation to get various Australia post service in your area please use our shipping postcode Thomastown, 3074 as the "from" address - https://auspost.com.au/parcels-mail/delivery-times.html?ilink=tools-open-deliv-times.

    Shipping Destinations

    We ship all products throughout mainland Australia, Tasmania and New Zealand - Including Darwin, Melbourne, Sydney, Tasmania, Adelaide, Brisbane, Perth, all metro and regional areas but do not deliver to areas in Australia where the Australia Post delivery network is not available. 

    Check Express shipping delivery coverage area at - http://auspost.com.au/parcels-mail/delivery-areas.html

    Receipt of deliveries

    Deliveries to post office boxes are not permitted where delivery is by courier. If delivery is by courier and nobody is available at the delivery address to accept delivery when delivery is attempted then the courier may either:

    • leave the relevant parcel at the unattended address (the courier will do so if specified in your delivery requirements); or
    • re-attempt delivery at a later time or date, in which case we may charge you an additional re-delivery fee. 

    Note that if a delivery is left unattended at the shipping address and is subsequently stolen then the theft is your responsibility, not ours.

    Payment & Security

    Apple Pay Google Pay Mastercard PayPal Visa

    Your payment information is processed securely. We do not store credit card details nor have access to your credit card information.

    You may also like