1. Home
  3. AIBOX-1684X AI Embedded PC Edge Computing Video Analysis

AIBOX-1684X AI Embedded PC Edge Computing Video Analysis

$369.00 USD
$369.00 USD
Shipping calculated at checkout.
  • American Express
  • Apple Pay
  • Google Pay
  • Mastercard
  • PayPal
  • Shop Pay
  • Union Pay
  • Visa
Brand: Firefly
Collections:
AIBOX-1684X AI Embedded PC Edge Computing Video Analysis
$369.00 USD
$369.00 USD

Discover AIBOX-1684X

AIBOX-1684X uses SOPHON AI processor BM1684X, which can be configured with 16GB large memory and 128GB eMMC; supports 32TOPS (INT8) peak computing power, 16TFLOPS (FP16/BF16) computing power, and 2TFLOPS (FP32) high-precision computing power; supports 32-channel H.265/H.264 1080p@25fps video decoding; supports mainstream programming frameworks, with a complete toolchain and high ease of use, and low algorithm migration cost; suitable for a variety of AI computing scenarios such as visual computing, edge computing, general computing services, smart transportation, unmanned supermarkets, and drones.

Soc

SOPHON BM1684X
Cpu

High-performance octa-core ARM A53, 12nm lithography process, frequency up to 2.3 GHz
Tpu

32TOPS (INT8)、16TFLOPS (FP16/BF16)、2TFLOPS (FP32)
Vpu
  • 32-channel H.265/H.264 1080P@25fps video decoding
  • 1-channel H.265 8K@25fps video decoding
  • 32-channel 1080P@25fps processing decoding + AI analysis
  • 12-channel H.265/H.264 1080P@25fps video encoding
  • JPEG image encoding and decoding can reach 1080P@600fps
Ram

8GB/12GB/16GB LPDDR4/LPDDR4X
Storage

32GB/64GB/128GB eMMC, 1 × TF Card
Power

DC 12V/4A (5.5 × 2.5mm)
Power consumption
  • Normal: 20.4W (12V/1700mA)
  • Max: 43.2W (12V/3600mA)
System

Linux
Software support
  • The private deployment of ultra-large-scale parameter models under the Transformer architecture, including large language models such as LLaMa2, ChatGLM, and Qwen, as well as major visual models like ViT, Grounding DINO, and SAM.
  • The private deployment of the Stable Diffusion V1.5 image generation model in the AIGC field.
  • Traditional network architectures such as CNN, RNN, and LSTM; a variety of deep learning frameworks, including TensorFlow, PyTorch, MXNet, PaddlePaddle, Caffe, and ONNX, as well as custom operator development.
  • Docker container management technology.
Dimension

90.6mm × 84.4mm × 48.5mm
Weight

≈ 420g
Environment
  • Operating temperature: -20℃～60℃
  • Storage temperature: -20℃～70℃
  • Storage humidity: 10%～90%RH (non-condensing)
Ethernet

2 × Gigabit Ethernet (1000Mbps/RJ45)
Usb

2 × USB3.0 (Max: 1A), 1 × Type-C (Debug serial)
Button

1 × Power button
Product tutorials Click Here
Sdk software and firmware files Click Here

Our cooperating carriers: FedEx, DHL, UPS

Delivery Area And Cost

Country/Region 0-2kg 2kg+
Japan, Taiwan, Hong Kong, Macau, Singapore, Thailand, Malaysia $15 $15 + $5 per kg
Indonesia, Philippines $25 $25 + $10 per kg
South Korea $25 $25 + $5 per kg
Finland, France, Germany, Greece, Ireland, Italy, Netherlands, Norway, Portugal, Spain, Sweden, Switzerland, United States, Australia, New Zealand, Austria, Belgium, Denmark $30 $45 + $10 per kg
Canada, United Kingdom $30 $30 + $10 per kg
Hungary, India, Israel, Laos, Myanmar, Poland, Saudi Arabia, Turkey, United Arab Emirates, Vietnam, Bangladesh, Qatar, Cyprus, Pakistan, Brunei, Sri Lanka, Jordan, Oman, Maldives, Bulgaria, Iceland, Slovakia, Lithuania, Romania, Albania, Armenia, Mexico, Nepal, Serbia, Cambodia, Croatia, Czech Republic, Slovenia $50 $50 + $15 per kg

 

Shipping Time (for reference only, the actual situation shall prevail):

Area  Shipping time
Europe 3 - 7 days
Asia, Oceania 3 - 7 days
North America 3 - 7 days
South America 5 - 10 days

Order preparation time: 3-7 days (specific details need to refer to the order situation).