0571-82835676

CH
PCIE
summarize scene specification
Inference Accelerator card R420

The GPU customer 2 AI chip is suitable for high-performance inference scenarios in data centers, and fully supports various artificial intelligence tasks such as natural language processing, computer vision, voice, and traditional machine learning.

Product
consult
Application scenario

  • Internet

  • Smart Finance

  • Smart Park

  • Intelligent Transportation
    Technical specification
    Name Specifications
    Accuracy INT8/INT16
    FP16/FP32
    Memory 16 GB GDDR6
    Memory bandwidth 512 GB/s
    System interconnection PClE 4.0x16 compatible 3.0/2.0/1.0
    Encoding/decoding capability 108 channel 1080P@30FPS decode
    Heat dissipation Passive
    ECC Support
    Application Reasoning, Training
    Power consumption 240W
    Size Full height Full length Double slot
    Operating temperature 0℃-45℃