Bringing generative AI capabilities to the edge
GPT Stable Diffusion ChatDoc
Hello, AI World
Powered by SOPHON SG2300x
- Octa-core A53,
up to 2.3GHz - Support 12 channels HD
hardware encoding - Support 32 channels HD
hardware decoding - Support INT8,
FP16/BF16 and FP32 - Mainstream frameworks Support :
- Built-in 24TOPS@INT8 high-performance TPU (Tensor Processing Unit)
Built-in High Computing Power TPU
24TOPS INT8
FP16/BF16
FP32
High Integration
Easy Secondary Development
Radxa x SOPHON AI SDK
Easily to Create Your Own AI Project
BMNNSDK one-stop toolkit provides a series of software tools including the underlying driver environment,
compiler and inference deployment tool. The easy-to-use and convenient toolkit covers
the model optimization, efficient runtime support and other capabilities required for neural network inference.
Supports 2x Module Cascades, up to 48T computing power
Computing Power
Provide PCIe X4 RC/EP
- Easily supports multiple perphials
- Supports use as a PCIe slave device
- SATA
- USB
- RS232
- RS485
- High-speed Devices
- ......
Made for secondary development
• Open Source
- AI Demo
- Linux SDK
• Hardware Reference Design Available
- Open BaseBoard Design
- BaseBoard Design Guide
- Datasheet
- Thermal Design Guide
- 3D Design
- 2D Design
Strong Codec Capability
Support 32 channels HD hardware decoding
Radxa Model Zoo
Support Ubuntu, CASA OS with web management panel
Applications
Public Security
Private GPT
Private Stable Diffusion
Smart Healthcare
Industrial AI
