ecs.ebmgn8is.32xlarge by Alibaba Cloud

ecs.ebmgn8is.32xlarge is a ecs.ebmgn8is family (128 vCPUs, 1024 GiB RAM, 0 GB storage, 8xL20 49152 GiB VRAM) server offered by Alibaba Cloud with 128 vCPUs, 1024 GiB of memory and 0 GB of storage.
128 vCPU
1024 GiB Memory
8 GPU
Spare SCore
-
(All-cores)
-
(Single-core)

Specifications

Server Metadata

Vendor ID
alicloud
Name
ecs.ebmgn8is.32xlarge
Description
ecs.ebmgn8is family (128 vCPUs, 1024 GiB RAM, 0 GB storage, 8xL20 49152 GiB VRAM)
Family
ecs.ebmgn8is
Hw Virt
-
Status
active
Observed At
2026-10-23T21:32:38.445354

Availability

REGION / IDSPOTONDEMAND

Processor

vCPUs
128
Hypervisor
KVM
CPU Allocation
Dedicated
CPU Speed
3.3 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
6462C

System Resources and Accelerators

MEMORY
Memory Amount
1 TB
ACCELERATORS
Accelerator Count
8
Accelerator Memory Min
48 GiB
Accelerator Memory Total
384 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Ada Lovelace
Accelerator Model
L20
Accelerators
    STORAGE
    Storage Size
    0 GB
    Storages
      NETWORK
      Network Speed Baseline
      170 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      Server Description

      An accelerated bare-metal platform featuring eight NVIDIA L20 GPUs and one terabyte of system memory for parallel computing workloads.

      GPU AcceleratedMemory Optimized

      Alibaba Cloud ecs.ebmgn8is.32xlarge is an x86_64 bare-metal server configured with 128 dedicated Intel Xeon 6462C vCPUs running at 3.3 GHz and 1024.0 GB of system memory. Acceleration is provided by eight NVIDIA L20 GPUs from the Ada Lovelace architecture, delivering a total of 384 GB of VRAM. The instance features a baseline network bandwidth of 170 Gbps and utilizes the KVM hypervisor. It contains no local storage, necessitating external storage attachments for persistent data. This high-density hardware configuration is designed for parallel processing tasks, making it suitable for distributed machine learning inference, model training, large-scale simulations, and rendering workloads.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Alternatives

      Servers of the Same Family

      INSTANCEvCPUsMEMORYAccelerators

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      ecs.ebmgn8is.32xlarge FAQs