Skip to main content

Artificial Intelligence

Radxa Orion O6 / O6N features up to 28.8 TOPS NPU computing power, supporting model deployment of INT4 / INT8 / INT16 / FP16 / BF16 and TF32 types.

The following documentation will provide detailed introduction to the complete model deployment workflow based on this chip P1 NPU SDK "NeuralOne", focusing on environment configuration, model compilation and quantization, and common model deployment cases.

    You need to be logged into GitHub to post a comment. If you are already logged in, please ignore this message.

    Radxa-docs © 2026 by Radxa Computer (Shenzhen) Co.,Ltd. is licensed under CC BY 4.0