logo

a2-ultragpu-4g by Google Cloud Platform

a2-ultragpu-4g is a Accelerator Optimized: 4 NVIDIA A100 80GB GPUs, 48 vCPUs, 680GB RAM, 4 local SSD server offered by Google Cloud Platform with 48 vCPUs, 680 GiB of memory and 1.61 TB of storage. The pricing starts at 1.8365 USD per hour.
48 vCPU
680 GiB Memory
1.61 TB Storage
4 GPU
Spare SCore
37882
(All-cores)
1195
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1020048
Name
a2-ultragpu-4g
Description
Accelerator Optimized: 4 NVIDIA A100 80GB GPUs, 48 vCPUs, 680GB RAM, 4 local SSD
Family
a2
Hw Virt
Status
active
Observed At
2026-08-06T12:09:15.627944

Availability

REGION / IDSPOTONDEMAND
Columbus (US) / us-east5
1.8365 USD/h 4.3985 USD/h
Council Bluffs (US) / us-central1
2.5393 USD/h 4.3985 USD/h
Eemshaven (NL) / europe-west4
2.4062 USD/h 4.842 USD/h
Ashburn (US) / us-east4
2.9721 USD/h 4.9533 USD/h
Jurong West (SG) / asia-southeast1
3.2557 USD/h 5.4256 USD/h

Processor

vCPUs
48
CPU Allocation
Dedicated
CPU Cores
24
CPU Speed
2.2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU L1D Cache
32 KiB
CPU L1D Cache Total
768 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
768 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
24 MiB
CPU L3 Cache
39 MiB
CPU L3 Cache Total
39 MiB
CPU Flags
fpu, vme, de, pse, tsc, msr, pae, mce, cx8, apic, sep, mtrr, pge, mca, cmov, pat, pse36, clflush, mmx, fxsr, sse, sse2, ss, ht, syscall, nx, pdpe1gb, rdtscp, lm, constant_tsc, rep_good, nopl, xtopology, nonstop_tsc, cpuid, tsc_known_freq, pni, pclmulqdq, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, ssbd, ibrs, ibpb, stibp, ibrs_enhanced, fsgsbase, tsc_adjust, bmi1, hle, avx2, smep, bmi2, erms, invpcid, rtm, mpx, avx512f, avx512dq, rdseed, adx, smap, clflushopt, clwb, avx512cd, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, arat, avx512_vnni, md_clear, arch_capabilities
Ecpus
31.7
Scalability
132.08

System Resources and Accelerators

MEMORY
Memory Amount
680 GiB
Memory Amount Actual
680 GiB
GPU
GPU Count
4
GPU Memory Min
80 GiB
GPU Memory Total
320 GiB
GPU Manufacturer
NVIDIA
GPU Family
Ampere
GPU Model
A100
GPUs
  • NVIDIA Ampere NVIDIA A100-SXM4-80GB (Memory amount: 81920, Firmware version: 535.183.01, BIOS version: 92.00.94.00.04, Clock rate: 1410)
  • NVIDIA Ampere NVIDIA A100-SXM4-80GB (Memory amount: 81920, Firmware version: 535.183.01, BIOS version: 92.00.94.00.04, Clock rate: 1410)
  • NVIDIA Ampere NVIDIA A100-SXM4-80GB (Memory amount: 81920, Firmware version: 535.183.01, BIOS version: 92.00.94.00.04, Clock rate: 1410)
  • NVIDIA Ampere NVIDIA A100-SXM4-80GB (Memory amount: 81920, Firmware version: 535.183.01, BIOS version: 92.00.94.00.04, Clock rate: 1410)
STORAGE
Storage Size
1608 GB
Storage Type
nvme ssd
Storages
  • 402 GB nvme ssd
  • 402 GB nvme ssd
  • 402 GB nvme ssd
  • 402 GB nvme ssd
NETWORK
Inbound Traffic
0 GB/month
Outbound Traffic
0 GB/month
IPv4
0

Server Description

An accelerator-optimized platform combining four NVIDIA A100 GPUs and 680GB RAM for demanding parallel processing and large language model inference.

GPU AcceleratedMemory Optimized

Google Cloud Platform a2-ultragpu-4g is an accelerator-optimized server designed for parallel computing workloads. It features four NVIDIA A100 Ampere GPUs with 320 GB of total VRAM, 48 vCPUs on an Intel Xeon x86_64 architecture, 680.0 GB of system memory, and 1608 GB of local NVMe SSD storage. Benchmark results show top-tier performance in LLM inference prompt processing and text generation for medium and large models. However, a key tradeoff is its weak single-core CPU performance, which falls into the bottom 25% in stress-ng and Geekbench single-core tests. Multi-core CPU and memory bandwidth benchmarks perform in the average tier. This server is optimized for deep learning, LLM inference, and data science workloads that require dense GPU acceleration, while being less efficient for single-threaded or general-purpose tasks.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

1.44Score
Precomputed compound score for Cache Intensive workloads. A weighted average (geometric mean) of benchmark scores compared to their medians: score = ∏ (x_i / m_i)^(w_i / Σw). The score of 1.0 represents a synthetic baseline server with the median performance of each component benchmark; 0.5 means roughly half the performance; and 2.0 means twice the performance of that reference profile. Component weights: 50% Redis RPS (pipeline=1, SET), 20% Redis RPS (pipeline=16, SET), 10% PassMark Memory Mark (composite), 10% Memory bandwidth (read, 16 MB ~ L3), 10% PassMark single-thread CPU. Rationale for component selection: In-memory key-value store workload, mixing direct Redis performance metrics with memory speed and latency benchmarks, and single-core CPU performance profiles.
Component Score Weight Impact
Raw Reference Normalized Target Actual
Redis RPS (pipeline=1, SET) 3,548,377 ops/sec 1,910,660 ops/sec 1.86 50.00% 50.00% +36.40%
Redis RPS (pipeline=16, SET) 20,539,926 ops/sec 11,608,287 ops/sec 1.77 20.00% 20.00% +12.10%
PassMark Memory Mark (composite) 2,265 2,416 0.937 10.00% 10.00% -0.65%
Memory bandwidth (read, 16 MB ~ L3) 89,817 MB/sec 107,896 MB/sec 0.832 10.00% 10.00% -1.82%
PassMark single-thread CPU 1,696 Mops/s 2,364 Mops/s 0.718 10.00% 10.00% -3.26%

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 1,051

Geekbench Multi-Core

Score: 10,350

Passmark CPU Scores

BENCHMARKSCORE
Mark
 30679
Compression
 518172
Encryption
 15662
Extended Instructions
 32899
Floating Point Maths
 68172
Integer Maths
 126890
Physics
 2398
Prime Numbers
 153
Single Threaded
 1696
String Sorting
 58640

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2265
Database Operations
 14059
Memory Latency
 56
Memory Read Cached
 20825
Memory Read Uncached
 7606
Memory Write
 7974

Stress-ng Raw Scores

Stress-ng Relative Multicore Performance

LLM Inference Speed for Prompt Processing

LLM Inference Speed for Text Generation

Static Web Server

Redis

Alternatives

Servers of the Same Family

INSTANCEvCPUsMEMORYGPUs
a2-highgpu-1g 1285 GiB1
a2-ultragpu-1g 12170 GiB1
a2-highgpu-2g 24170 GiB2
a2-ultragpu-2g 24340 GiB2
a2-highgpu-4g 48340 GiB4
a2-highgpu-8g 96680 GiB8
a2-ultragpu-8g 961360 GiB8

Similar Servers

INSTANCEVENDORvCPUsMEMORYGPUs

a2-ultragpu-4g FAQs