
AceleMax AG-160
1U 6x GPU Server
- Deep Learning Training and Inference
Reference # Q710040
Processor
- Single AMD EPYC™ 7002/7003 Series Processor
Chipset
- SoC
GPU Support & Quantity
- Up to 6 x Tesla T4 or 4 x Tesla V100 PCIe
System Memory (Maximum)
- 16 DDR4 DIMM slots
- 8-Channel memory architecture
- Up to 2,048GB RDIMM/ 1,024GB LRDIMM/ 2,048GB LRDIMM 3DS
- Memory speed: 2666/2400 MHz
Expansion Slots
- 6 x PCIe G3 x16 slots for GPUs
- 1 x FH/HL PCIe G3 x16
Connectivity
- 2 x 10GBASE-T ports
- 1 x RJ45 Dedicated IPMI LAN port
VGA
- Aspeed AST2500 BMC
Management
- Intelligent Platform Management Interface v.2.0
- IPMI 2.0 + KVM with dedicated LAN
Drive Bays
- 2 x hot-swap 2.5” SATA 6G Drive Bays
- 2 x SATA 6G SATADOM ports
- 2 x NVME/SATA M.2 2280/22110 slots
Power Supply
- 1 + 1 1600 watt redundant PSUs, 80 PLUS Platinum
System Dimensions
- 1.71″ x 17.24″ x 34.84” / 43.5mm x 438mm x 885mm (H x W x D)
Optimized for Turnkey Solutions
Enable powerful design, training, and visualization with built-in software tools including TensorFlow, Caffe, Torch, Theano, BIDMach cuDNN, NVIDIA CUDA Toolkit and NVIDIA DIGITS.




