AI Server For AI, Deep / Machine Learning & HPC

Using NVIDIA A100 Tensor Core GPU, up to 40GB HBM2 video memory

Supporting NVIDIA Ampere architecture, providing up to 19.5 TFLOPS of GPU FP32 performance

Equipped with Intel Xeon processors, up to 44 cores/88 threads

Rich I/O interfaces, including PCIe 4.0, NVMe SSD, etc.

Supporting AI acceleration frameworks such as CUDA, TensorRT, cuDNN, etc.

Deep learning model training

Natural language processing

Computer vision

Speech recognition

Financial modeling

Using the NVIDIA RTX 4090 GPU, up to 24GB GDDR6X video memory

Supporting the NVIDIA Ada Lovelace architecture, providing up to 83 TFLOPS of GPU FP32 performance

Equipped with Intel Xeon processors, up to 36 cores/72 threads

Supporting high-speed I/O interfaces such as PCIe 5.0 and NVMe SSD

Supporting AI acceleration frameworks such as CUDA, TensorRT, and cuDNN

High-performance AI model training

Computer vision

Natural language processing

Graphics rendering

Data analysis

Uses the NVIDIA V100 Tensor Core GPU, up to 32GB HBM2 memory

Supports the NVIDIA Volta architecture, providing up to 14 TFLOPS of GPU FP32 performance

Equipped with Intel Xeon processors, up to 44 cores/88 threads

Supports high-speed I/O interfaces such as PCIe 3.0 and NVMe SSD

Supports AI acceleration frameworks such as CUDA, TensorRT, and cuDNN

Deep learning model training

Large-scale data analysis

Scientific computing

High-performance rendering

NVIDIA RTX 6000 GPU, up to 48GB GDDR6 memory

Supports NVIDIA Ampere architecture, providing up to 38.7 TFLOPS GPU FP32 performance

Equipped with Intel Xeon processor, up to 36 cores/72 threads

Supports high-speed I/O interfaces such as PCIe 4.0 and NVMe SSD

Supports AI acceleration frameworks such as CUDA, TensorRT, and cuDNN

Professional-grade 3D rendering

High-performance scientific computing

Large-scale data analysis

AI model training

Industrial simulation