g4ad.2xlarge by Amazon Web Services

g4ad.2xlarge is a Graphics intensive [AMD processors] [Instance store volumes] Gen4 2xlarge server offered by Amazon Web Services with 8 vCPUs, 32 GiB of memory and 300 GB of storage. The pricing starts at 0.1685 USD per hour.
8 vCPU
32 GiB Memory
300 GB Storage
1 GPU
Spare SCore
3,051
(All-cores)
763
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
g4ad.2xlarge
Description
Graphics intensive [AMD processors] [Instance store volumes] Gen4 2xlarge
Family
g4ad
Hw Virt
Status
active
Observed At
2026-10-26T14:24:20.997109

Availability

REGION / IDSPOTONDEMAND
Quebec (CA) / ca-central-1
0.24555 USD/h -
London (GB) / eu-west-2
0.25065 USD/h -
Northern Virgina (US) / us-east-1
0.240025 USD/h -
Frankfurt (DE) / eu-central-1
0.2453 USD/h -
Dublin (IE) / eu-west-1
0.2745 USD/h -
Oregon (US) / us-west-2
0.2798 USD/h -
Ohio (US) / us-east-2
0.3434 USD/h -
Tokyo (JP) / ap-northeast-1
0.5424 USD/h -

Processor

vCPUs
8
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
4
CPU Speed
3 GHz
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
7R32
CPU L1D Cache
32 KiB
CPU L1D Cache Total
128 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
128 KiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
2 MiB
CPU L3 Cache
16 MiB
CPU L3 Cache Total
16 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, ht, syscall, nx, mmxext, fxsr_opt, pdpe1gb, rdtscp, lm, constant_tsc, rep_good, nopl, nonstop_tsc, cpuid, extd_apicid, aperfmperf, tsc_known_freq, pni, pclmulqdq, ssse3, fma, cx16, sse4_1, sse4_2, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, cmp_legacy, cr8_legacy, abm, sse4a, misalignsse, 3dnowprefetch, topoext, ssbd, ibrs, ibpb, stibp, vmmcall, fsgsbase, bmi1, avx2, smep, bmi2, rdseed, adx, smap, clflushopt, clwb, sha_ni, xsaveopt, xsavec, xgetbv1, clzero, xsaveerptr, rdpru, wbnoinvd, arat, npt, nrip_save, rdpid
Ecpus
4
Scalability
100

System Resources and Accelerators

MEMORY
Memory Amount
32 GiB
Memory Amount Actual
32 GiB
Memory Generation
DDR4
Memory Speed
2933 Mhz
ACCELERATORS
Accelerator Count
1
Accelerator Memory Min
8 GiB
Accelerator Memory Total
8 GiB
Accelerator Type
GPU
Accelerator Manufacturer
AMD
Accelerator Family
Radeon Pro Navi
Accelerator Model
V520
Accelerators
  • AMD Radeon Pro V520 (Memory amount: 8192)
STORAGE
Storage Size
300 GB
Storage Type
nvme ssd
Storages
  • 300 GB nvme ssd
NETWORK
Network Speed Baseline
4.167 Gbps
Network Speed Max
10 Gbps
Network Storage Speed Baseline
0.8 Gbps
Network Storage Speed Max
3.17 Gbps
Inbound Traffic
0 GB/month
Outbound Traffic
0 GB/month
IPv4
0

CPU and System Topology

Server Description

A GPU-accelerated instance featuring dedicated AMD graphics and local NVMe storage for graphics-intensive workloads and remote workstations.

GPU AcceleratedGeneral PurposeStorage & Database

Amazon Web Services g4ad.2xlarge is a GPU-accelerated instance featuring an AMD EPYC 7R32 processor with 8 vCPUs, 32.0 GB of DDR4 RAM, and a dedicated AMD Radeon Pro Navi V520 GPU with 8 GB of VRAM. Built on the Nitro hypervisor, it includes 300 GB of local NVMe SSD storage and a 4 Gbps baseline network bandwidth. Benchmark data shows average performance in Geekbench single-core and multi-core tests, alongside moderate results in image processing and software compilation. However, it exhibits performance tradeoffs, including weak large-block memory bandwidth and poor single-core stress-ng CPU performance. Qualitatively, the instance provides a cost-effective entry point for GPU-accelerated workloads that do not demand high-end enterprise compute. It is well-suited for graphics-intensive applications, remote workstations, and lightweight GPU tasks.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

0.43Score
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) 655,688 ops/sec 1,919,289 ops/sec 0.35 50.00% 50.00% -41.00%
Redis RPS (pipeline=16, SET) 4,344,794 ops/sec 11,728,058 ops/sec 0.36 20.00% 20.00% -18.00%
PassMark Memory Mark (composite) 2,544 2,416 1 10.00% 10.00% 0.00%
Memory bandwidth (read, 16 MB ~ L3) 37,166 MB/sec 108,466 MB/sec 0.34 10.00% 10.00% -10.00%
PassMark single-thread CPU 2,142 Mops/s 2,365 Mops/s 0.88 10.00% 10.00% -1.30%

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 1,339

Geekbench Multi-Core

Score: 5,215

Passmark CPU Scores

BENCHMARKSCORE
Mark
 10,560
Compression
 120,722
Encryption
 8,510
Extended Instructions
 7,338
Floating Point Maths
 16,063
Integer Maths
 26,910
Physics
 1,016
Prime Numbers
 43
Single Threaded
 2,142
String Sorting
 17,243

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2,544
Database Operations
 2,851
Memory Latency
 50
Memory Read Cached
 24,648
Memory Read Uncached
 12,806
Memory Write
 13,407

Stress-ng Stressors

CPU integerSingleMultiScaling
atomic
 385.98 366.48 0.95×
bitops
 119,887 601,511 5.02×
branch
 151,709 1,051,011 6.93×
funccall
 493.68 2,677 5.42×
funcret
 13,939 85,112 6.11×
hash
 131,200 816,358 6.22×
intmath
 19,436 84,192 4.33×
nop
 234,555 947,032 4.04×
prime
 343,935 1,827,800 5.31×
rotate
 59,449 247,499 4.16×
str
 608,373 3,244,918 5.33×
wcs
 472,506 2,140,576 4.53×
CryptographySingleMultiScaling
crypt
 2,802 12,159 4.34×
CompressionSingleMultiScaling
jpeg
 637.23 3,485 5.47×
zlib
 49.96 321.22 6.43×
HypervisorSingleMultiScaling
clock
 19,455 104,094 5.35×
clone
 203.47 724.53 3.56×
context
 3,321 22,748 6.85×
cpu-sched
 63.65 532.91 8.37×
eventfd
 24,758 421,241 17.01×
fault
 8,198 46,109 5.62×
fork
 3,741 21,118 5.64×
getrandom
 36,050 193,881 5.38×
hrtimers
 256,002 524,376 2.05×
mprotect
 1,049,277 1,477,385 1.41×
mtx
 16,181,228 342,091,942 21.14×
munmap
 2,431 14,859 6.11×
null
 408,421 2,657,218 6.51×
pipe
 1,710,288 2,561,457 1.50×
priv-instr
 422,825 2,844,138 6.73×
resched
 1,340,049 458,545 0.34×
switch
 33,873 1,061,961 31.35×
timermix
 131,344 900,081 6.85×
tlb-shootdown
 11,044 19,623 1.78×
tsc
 648,727 5,042,000 7.77×
usersyscall
 287,910 1,948,307 6.77×
vdso
 78,510,518 438,569,491 5.59×
vfork
 20,151 103,239 5.12×
x86syscall
 5,222,807 33,890,004 6.49×
yield
 3,161,260 3,427,777 1.08×
zero
 2,081,970 13,310,990 6.39×
CPU float/SIMDSingleMultiScaling
eigen
 12,288 58,164 4.73×
expmath
 2,763 17,461 6.32×
fma
 736,094 4,642,518 6.31×
fp
 206.36 1,167 5.65×
fractal
 6.4 40 6.25×
hyperbolic
 3,608 21,757 6.03×
logmath
 4,069 23,826 5.86×
matrix
 2,614 19,774 7.57×
matrix-3d
 518.92 1,254 2.42×
monte-carlo
 182.86 1,200 6.56×
mpfr
 1,263 6,550 5.19×
powmath
 1,330 8,609 6.47×
trig
 1,548 9,481 6.12×
veccmp
 16,899 82,818 4.90×
vecfp
 1,374 8,198 5.97×
vecmath
 3,335 21,545 6.46×
vecshuf
 477.83 2,361 4.94×
vecwide
 26,088 126,495 4.85×
AlgorithmsSingleMultiScaling
bitonicsort
 6.8 33.6 4.94×
bsearch
 224.77 1,133 5.04×
bubblesort
 0.8 3.2 4.00×
fibsearch
 255.89 1,314 5.14×
heapsort
 8.6 48 5.58×
hsearch
 5,277 25,381 4.81×
insertionsort
 6.6 30.6 4.64×
malloc
 2,600,640 15,913,383 6.12×
mcontend
 236.25 1,481 6.27×
mergesort
 25.6 156.99 6.13×
qsort
 16.6 100.6 6.06×
skiplist
 5,456 34,858 6.39×
tree
 1.8 4.8 2.67×
MemorySingleMultiScaling
cache
 513,324 1,309,806 2.55×
cachehammer
 271,744 2,118,188 7.79×
cacheline
 53.38 431.64 8.09×
l1cache
 196.12 760.37 3.88×
memcpy
 353.23 1,467 4.15×
memrate
 1.95 4.61 2.36×
memthrash
 57.98 278.15 4.80×
ptr-chase
 29,639,306 68,734,422 2.32×
spinmem
 225.59 393.96 1.75×
stream
 178.01 2,246 12.62×
vm
 54,227 291,485 5.38×

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

INSTANCEvCPUsMEMORYAccelerators
g4ad.xlarge 416 GiB1
g4ad.4xlarge 1664 GiB1
g4ad.8xlarge 32128 GiB2
g4ad.16xlarge 64256 GiB4

Similar Servers

INSTANCEVENDORvCPUsMEMORYAccelerators

g4ad.2xlarge FAQs