This site uses cookies. By continuing to browse the site you are agreeing to our use of cookies. Read our privacy policy>Search

If you need help, please click here:

Atlas 800 AI Inference Server (Model: 3000)

Powered by the Ascend 310 chip, the Atlas 800 AI inference server (model: 3000) supports up to 8 Atlas 300 AI inference accelerator cards for powerful real-time inference. It is widely used in AI inference scenarios at the data center side.

Huawei

Specifications

Parameters Atlas 800 AI Inference Server
Model: 3000
Form Factor 2U 2-socket AI server
Processor 2 Kunpeng 920 processors
Memory 32 DDR4 DIMM slots, up to 2933 MT/s
AI Accelerator Card Up to 8 Atlas 300 AI accelerator cards for 512-channel intelligent video analytics of people, vehicles, and objects
AI Computing Power 512 TOPS INT8
NPU Memory Up to 256 GB, total bandwidth up to 1638.4 Gbit/s
Local Storage • 25 x 2.5'' SAS/SATA HDDs or SSDs
• 12 x 3.5'' SAS/SATA HDDs or SSDs
• 8 x 2.5'' SAS/SATA HDDs or SSDs + 12 x 2.5'' NVMe SSDs
RAID RAID 0, 1, 5, 6, 10, 50, or 60
PCIe Up to 9 PCIe 4.0 slots: 8 PCIe standard slots and 1 PCIe slot for the RAID controller card
Power Supply 2 hot-swappable 900 W or 2000 W AC PSUs in 1+1 redundancy mode
Fan Module 4 hot-swappable fan modules in N+1 redundancy mode
Operating Temperature 5°C to 40 °C (41°F to 104°F)
Dimensions (H x W x D) 86.1 mm x 447 mm x 790 mm (3.39 in. x 17.60 in. x 31.10 in.)

For Partners

If you are already a Partner, please click here to get more marketing resources.
Click here to visit the Partner zone to check enquiry status, manage orders, get support, or learn more about Huawei Partners.

Share link to: