Home > FireFly > AIBOX-1688 AI Box - Loacl Large Models into a Small Box, 8GB RAM 32GB ROM, Up to 16 TOPS for AI deployment ChatGLM Qwen CNND TensorFlow PyTorch

1/1

AIBOX-1688 AI Box - Loacl Large Models into a Small Box, 8GB RAM 32GB ROM, Up to 16 TOPS for AI deployment ChatGLM Qwen CNND TensorFlow PyTorch

Name: AIBOX-1688 AI Box - Loacl Large Models into a Small Box, 8GB RAM 32GB ROM, Up to 16 TOPS for AI deployment ChatGLM Qwen CNND TensorFlow PyTorch
Brand: youyeetoo geeker shop
SKU: TQDPAIBO1688
Price: 232.6 USD
Availability: InStock

SKU: TQDPAIBO1688

The AIBOX-1688 is a compact AI device designed for the private deployment of major AI models. It is powered by the BM1688, a SOPHON AI processor with an octa-core ARM Cortex-A53, operating at 1.6 GHz. Equipped with a neural network acceleration engine TPU, it delivers peak performance of 32T@INT4,16T@INT8,4T@FP16/BF16, and 0.5T@FP32. With support for mainstream programming frameworks, this processor can be widely used in Al inference, computer vision, and more.

0.0 (0 Reviews)

$232.60

Received successfully

Coupon Code

CONTINUE SHOPPING

Add to Favorites (0)

1/1

Description
Reviews

AIBOX-1688 UP to 16TOPS, Loacl Large Models Small Box

Quick Start [Click here]
Tips
- If you want higher performance please click here：[Click here]

Introduction

AIBOX-1688 is an AI edge computing device powered by the SOPHON BM1688 SOC, featuring an octa-core ARM A53 CPU and a TPU that provides up to 32 TOPS of AI performance. It supports 8GB LPDDR4 memory and offers strong video processing capabilities with H.264/H.265 decoding and encoding support. The system also accommodates various deep learning frameworks and Docker container management, making it suitable for diverse AI applications in edge computing environments.

Features

1. [16TOPS BM1688 Al processor] BM1688 the SOPHON Al processor, features an octa-core ARM Cortex-A53 with up to 1.6 GHz of frequency. Equipped with a neural network acceleration engine TPU, it delivers peak performance of 32T@INT4 16T@INT8,4T@FP16/8F16, and 0.5T@FP32. With support for mainstream programming frameworks, this processor can be widely used in Al inference, computer vision, and more.
2. [Strong Network Communication Capability] With dual 1000Mbps Ethernet, the Al box ensures high-speed and stable network communication, meeting the needs of various application scenarios.
3. [Multi-channelvideo Al performance] The Al box supports up to 16 channels of H.265 /H.264 1080P video decoding, 10 channels of H.265 / H.264 1080P video encoding, and 16 channels of 1080p HD video processing (decoding + Al analysis). This meets the needs of various Al applications such as face detection on video streaming, license plate recognition, and smart cities.
4. [Software Support]The private deployment of ultra-large-scale parameter models under the Transformer architecture.Traditional network architectures such as CNN, RNN, and LSTM, various deep learning frameworks, including TensorFlow, PyTorch, MXNet, PaddlePaddle, and ONNX, as well as custom operator development.Docker container management technology.
5. [All-aluminum alloy enclosure for heat dissipation] The industrial-grade al-metal enclosure with an aluminum alloy structure for thermal conduction, The side of the top cover features a grille design for external airflow and efficient heat dissipation, ensuring computing performance and stability even under high-temperature operating conditions.

Shipping List

1 x AΙBOX-1688
1 x USB Cable
1 x 12V3A Adapter

Applications

visual computing, edge computing, general arithmetic services, intelligent transportation, unmanned supermarkets, drones

Specification

SOC:
- SOPHON BM1688
- Octa-core ARM Cortex-A53 @ 1.6GHZ
TPU:
- Built-in SOPHG0 neural network acceleration engine TPU, 32T@INT4 peak computing power,
  16T@INT8 peak computing power,4T@FP16/BF16computing power, 0.5T@FP32 computing power
Decoding/Encoding:
- Video decoding: H.264/H.265 decoding (Max performance: 1920*1080@480FPS or 3840*2160 @120FPS)
- Video encoding:H.264/H.265 encoding(Max performance:1920*1080@300FPS or 3840* 2160 @75 FPS)
- Image codec: jPEG/MjPEG Baseline codec (jPEG codec with a maximum resolution of 1080P@480 FPS)
RAM:
- 8GBLPDDR4(4GB/8GB/16GB optional)
Storage:
- 32GB eMMC(32GB/64GB/128GB/256GB optional)
Power:
- DC12V/3A(DC5.5*2.1mm)
OS:
- Linux

Detailed Descriptions

Your feedback matters! By leaving a review, you can help other shoppers make informed decisions and help us improve our products and services. We value your opinion and appreciate you taking the time to share your experience with us.