g7e.4xlarge by Amazon Web Services

g7e.4xlarge is a Graphics intensive [Extra storage or memory] Gen7 4xlarge server offered by Amazon Web Services with 16 vCPUs, 128 GiB of memory and 1.9 TB of storage. The pricing starts at 1.3753 USD per hour.
16 vCPU
128 GiB Memory
1.9 TB Storage
1 GPU
Spare SCore
17,742
(All-cores)
2,166
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
g7e.4xlarge
Description
Graphics intensive [Extra storage or memory] Gen7 4xlarge
Family
g7e
Hw Virt
Status
active
Observed At
2026-11-04T10:36:34.707694

Availability

REGION / IDSPOTONDEMAND
Northern Virgina (US) / us-east-1
1.5914 USD/h 3.9982 USD/h
Oregon (US) / us-west-2
3.4205 USD/h 3.9982 USD/h
Ohio (US) / us-east-2
2.672 USD/h 3.9982 USD/h
Aragón (ES) / eu-south-2
2.64835 USD/h 4.213 USD/h
Seoul (KR) / ap-northeast-2
4.424 USD/h 4.9155 USD/h
Stockholm (SE) / eu-north-1
2.31835 USD/h 5.7677 USD/h
Tokyo (JP) / ap-northeast-1
2.9856 USD/h 5.7985 USD/h
Mumbai (IN) / ap-south-1
4.59215 USD/h 6.5302 USD/h
Frankfurt (DE) / eu-central-1
3.38505 USD/h 6.7991 USD/h
(MY) / ap-southeast-5
- 6.8496 USD/h
(TH) / ap-southeast-7
- 6.8496 USD/h
London (GB) / eu-west-2
2.1077 USD/h 6.949 USD/h
Jakarta (ID) / ap-southeast-3
3.5345 USD/h 7.6113 USD/h

Processor

vCPUs
16
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
8
CPU Speed
2.4 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
8559C
CPU L1D Cache
48 KiB
CPU L1D Cache Total
384 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
256 KiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
16 MiB
CPU L3 Cache
320 MiB
CPU L3 Cache Total
320 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, arch_perfmon, rep_good, nopl, xtopology, nonstop_tsc, cpuid, aperfmperf, tsc_known_freq, pni, pclmulqdq, monitor, ssse3, fma, cx16, pdcm, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, tsc_deadline_timer, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, cpuid_fault, ssbd, ibrs, ibpb, stibp, ibrs_enhanced, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, erms, invpcid, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, avx_vnni, avx512_bf16, wbnoinvd, ida, arat, avx512vbmi, umip, pku, ospke, waitpkg, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, tme, avx512_vpopcntdq, rdpid, cldemote, movdiri, movdir64b, md_clear, serialize, amx_bf16, avx512_fp16, amx_tile, amx_int8, flush_l1d, arch_capabilities
Ecpus
8.2
Scalability
51.25

System Resources and Accelerators

MEMORY
Memory Amount
128 GiB
Memory Amount Actual
128 GiB
Memory Generation
DDR5
Memory Speed
5600 Mhz
ACCELERATORS
Accelerator Count
1
Accelerator Memory Min
96 GiB
Accelerator Memory Total
96 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Blackwell
Accelerator Model
RTX PRO 6000
Accelerators
  • NVIDIA Blackwell NVIDIA RTX PRO 6000 Blackwell Server Edition (Memory amount: 97887, Firmware version: 590.48.01, BIOS version: 98.02.9E.00.03, Clock rate: 2430)
STORAGE
Storage Size
1900 GB
Storage Type
nvme ssd
Storages
  • 1900 GB nvme ssd
NETWORK
Network Speed Baseline
50 Gbps
Network Speed Max
50 Gbps
Network Storage Speed Baseline
8 Gbps
Network Storage Speed Max
8 Gbps
Inbound Traffic
0 GB/month
Outbound Traffic
0 GB/month
IPv4
0

CPU and System Topology

Server Description

High-capacity GPU instance featuring NVIDIA Blackwell graphics, high-speed NVMe storage, and top-tier LLM inference capabilities for demanding visual and machine learning workloads.

GPU AcceleratedStorage & DatabaseGeneral Purpose

Amazon Web Services g7e.4xlarge is a GPU-accelerated server instance designed for graphics-intensive and AI workloads. Built on the AWS Nitro hypervisor, it features 16 vCPUs and 8 physical cores via an Intel Xeon 8559C processor running at 2.4 GHz, paired with 128.0 GB of DDR5 system memory and 320 MB of L3 cache. Compute acceleration is provided by a single NVIDIA Blackwell RTX PRO 6000 GPU featuring 96 GB of dedicated VRAM. The instance includes a 1900 GB local NVMe SSD and a 50 Gbps baseline network capacity. Benchmark results demonstrate top-tier performance in single-core tasks and large language model inference across 135M, 7B, and 70B parameter models, alongside solid single-threaded compression throughput. Multi-core processor scores and memory bandwidth align with average industry baselines. This server is well suited for LLM inference, high-resolution rendering, and data science pipelines requiring local high-speed storage.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

1.6Score
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) 3,292,702 ops/sec 1,933,252 ops/sec 1.7 50.00% 50.00% +30.00%
Redis RPS (pipeline=16, SET) 16,876,370 ops/sec 11,794,699 ops/sec 1.4 20.00% 20.00% +7.00%
PassMark Memory Mark (composite) 2,704 2,412 1.1 10.00% 10.00% +0.96%
Memory bandwidth (read, 16 MB ~ L3) 261,185 MB/sec 108,490 MB/sec 2.4 10.00% 10.00% +9.10%
PassMark single-thread CPU 3,237 Mops/s 2,365 Mops/s 1.3 10.00% 10.00% +2.70%

GPU Bandwidth and Latency

Node (all GPUs)
Node baseline directional bandwidth
50.2 GB/s
Node GPU-to-host bandwidth
57.2 GB/s
Node host-to-GPU bandwidth
55.5 GB/s
Single GPU slot
Per-GPU GPU-to-host bandwidth
57.2 GB/s
Per-GPU host-to-GPU bandwidth
55.6 GB/s
Per-GPU host-device latency
985 ns
Benchmark Environment
Driver Version
 590.48.01
CUDA Version (driver)
 13.1
nvbandwidth Version
 v0.5
GPU Count
 1
P2P Supported
No
Efficiency
SM/CE copy efficiency
0.93

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 2,336

Geekbench Multi-Core

Score: 13,929

Passmark CPU Scores

BENCHMARKSCORE
Mark
 29,391
Compression
 308,307
Encryption
 18,654
Extended Instructions
 24,706
Floating Point Maths
 60,151
Integer Maths
 84,933
Physics
 3,949
Prime Numbers
 165
Single Threaded
 3,237
String Sorting
 42,420

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2,704
Database Operations
 10,384
Memory Latency
 51
Memory Read Cached
 27,961
Memory Read Uncached
 9,787
Memory Write
 9,650

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
g7e.2xlarge 864 GiB1
g7e.8xlarge 32256 GiB1
g7e.12xlarge 48512 GiB2
g7e.24xlarge 961024 GiB4
g7e.48xlarge 1922048 GiB8

Similar Servers

INSTANCEVENDORvCPUsMEMORYAccelerators

g7e.4xlarge FAQs