Specifications
MOQ :
1 piece
Output Interface Type :
support HDMI input, DP
Interconnect :
x16 PCIe
Interface :
PCI Express 4.0
Private Mold :
Yes
Memory Bandwidth :
760 GB/s
Memory Capacity :
40Gb
Nvidia Cuda Cores :
3,328
Memory Interface :
384 Bit
Outputs :
HDMI 2.1, DisplayPort 1.4a
Psu Recommendation :
350 Watts Minimum
Delivery Time :
2-7days
Ray Tracing Cores :
68
Application :
Workstation, Workstation
Price :
$2955-4500/UNIT
Status :
In stock
Model Number :
A30
Memory Bus Width :
320-bit
Description
A30 Enterprise GPU with ECC NVLink Video Decoder Multi-Instance GPU
Product Overview

The A30 is an Ampere GA100 data center GPU engineered for AI workloads, high-performance computing, and multi-tenant virtualization environments.

Key Features
  • Equipped with 24GB HBM2 ECC memory and 933GB/s high bandwidth
  • Delivers up to 330 TOPS INT8 performance for fast AI inference and supports lightweight model training
  • Features MIG technology, enabling division into up to 4 independent GPU instances for resource isolation
  • Integrates video decoding engines and supports PCIe 4.0 and NVLink
  • With 165W TDP and passive cooling, this dual-slot GPU ensures reliable 24/7 operation for enterprise data centers
Send your message to this supplier
Send Now

A30 Enterprise GPU with ECC NVLink Video Decoder Multi Instance GPU

Ask Latest Price
MOQ :
1 piece
Output Interface Type :
support HDMI input, DP
Interconnect :
x16 PCIe
Interface :
PCI Express 4.0
Private Mold :
Yes
Memory Bandwidth :
760 GB/s
Contact Supplier
A30 Enterprise GPU with ECC NVLink Video Decoder Multi Instance GPU

Wuhan Jinnuo Maotong Technology Co., Ltd.

Verified Supplier
1 Years
hubei, wuhan
Since 2025
Business Type :
Agent, Exporter, Seller
Total Annual :
2985074-7462686
Employee Number :
>120
Certification Level :
Verified Supplier
Contact Supplier
Submit Requirement