logo

g6e.4xlarge by Amazon Web Services

g6e.4xlarge is a Graphics intensive [Extra storage or memory] Gen6 4xlarge server offered by Amazon Web Services with 16 vCPUs, 128 GiB of memory and 600 GB of storage. The pricing starts at 0.712 USD per hour.
16 vCPU
128 GiB Memory
600 GB Storage
1 GPU
Spare SCore
23941
(All-cores)
2992
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
g6e.4xlarge
Description
Graphics intensive [Extra storage or memory] Gen6 4xlarge
Family
g6e
Hw Virt
Status
active
Observed At
2026-07-29T19:07:27.195236

Availability

REGION / IDSPOTONDEMAND
Oregon (US) / us-west-2
1.7176 USD/h 3.0042 USD/h
Ohio (US) / us-east-2
1.359367 USD/h 3.0042 USD/h
Northern Virgina (US) / us-east-1
2.898925 USD/h 3.0042 USD/h
Aragón (ES) / eu-south-2
0.98415 USD/h 3.1657 USD/h
Stockholm (SE) / eu-north-1
1.1173 USD/h 3.1867 USD/h
Hyderabad (IN) / ap-south-2
0.7971 USD/h 3.608 USD/h
Mumbai (IN) / ap-south-1
1.01595 USD/h 3.608 USD/h
United Arab Emirates / me-central-1
1.5087 USD/h 3.6855 USD/h
Seoul (KR) / ap-northeast-2
1.433 USD/h 3.6936 USD/h
Frankfurt (DE) / eu-central-1
1.811667 USD/h 3.7565 USD/h
Osaka (JP) / ap-northeast-3
1.7133 USD/h 4.357 USD/h
Tokyo (JP) / ap-northeast-1
1.69905 USD/h 4.357 USD/h

Processor

vCPUs
16
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
8
CPU Speed
3.4 GHz
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
7R13
CPU L1D Cache
32 KiB
CPU L1D Cache Total
256 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
256 KiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
4 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
32 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, pcid, sse4_1, sse4_2, x2apic, 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, invpcid, rdseed, adx, smap, clflushopt, clwb, sha_ni, xsaveopt, xsavec, xgetbv1, clzero, xsaveerptr, rdpru, wbnoinvd, arat, npt, nrip_save, vaes, vpclmulqdq, rdpid
Ecpus
8
Scalability
100

System Resources and Accelerators

MEMORY
Memory Amount
128 GiB
Memory Amount Actual
128 GiB
Memory Generation
DDR4
Memory Speed
3200 Mhz
GPU
GPU Count
1
GPU Memory Min
45 GiB
GPU Memory Total
45 GiB
GPU Manufacturer
NVIDIA
GPU Family
Ada Lovelace
GPU Model
L40S
GPUs
  • NVIDIA Ada Lovelace NVIDIA L40S (Memory amount: 46068, Firmware version: 590.48.01, BIOS version: 95.02.66.00.15, Clock rate: 2520)
STORAGE
Storage Size
600 GB
Storage Type
nvme ssd
Storages
  • 600 GB nvme ssd
NETWORK
Network Speed Baseline
20 Gbps
Network Speed Max
20 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

A GPU-accelerated instance combining dedicated AMD EPYC processing, local NVMe storage, and NVIDIA Ada Lovelace graphics for high-performance inference.

GPU AcceleratedMemory OptimizedStorage & Database

Amazon Web Services g6e.4xlarge is a graphics-intensive instance designed for GPU-accelerated workloads. It is equipped with an AMD EPYC 7R13 processor offering 16 vCPUs, 128.0 GB of DDR4 memory, and a 600 GB local NVMe SSD. The system features a single NVIDIA Ada Lovelace L40S GPU with 45 GB of VRAM. Performance benchmarks show top-tier capabilities in LLM inference, processing 13568.43 tokens per second for small models and 885.42 tokens per second for large models. Single-core CPU performance is strong, though multi-core operations and large-block memory bandwidth are average to weak. This hardware profile provides a cost-efficient balance of high VRAM and local storage, making it highly suitable for machine learning inference, graphics rendering, and data processing.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

0.774Score
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) 1,385,268 ops/sec 1,896,415 ops/sec 0.73 50.00% 50.00% -14.60%
Redis RPS (pipeline=16, SET) 10,256,441 ops/sec 11,539,523 ops/sec 0.889 20.00% 20.00% -2.33%
PassMark Memory Mark (composite) 2,624 2,411 1.09 10.00% 10.00% +0.87%
Memory bandwidth (read, 16 MB ~ L3) 41,536 MB/sec 107,368 MB/sec 0.387 10.00% 10.00% -9.06%
PassMark single-thread CPU 2,644 Mops/s 2,363 Mops/s 1.12 10.00% 10.00% +1.14%

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 1,694

Geekbench Multi-Core

Score: 9,945

Passmark CPU Scores

BENCHMARKSCORE
Mark
 23714
Compression
 281002
Encryption
 18934
Extended Instructions
 16510
Floating Point Maths
 40363
Integer Maths
 73649
Physics
 2147
Prime Numbers
 104
Single Threaded
 2644
String Sorting
 38499

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2624
Database Operations
 7220
Memory Latency
 66
Memory Read Cached
 26516
Memory Read Uncached
 17159
Memory Write
 17559

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
g6e.xlarge 432 GiB1
g6e.2xlarge 864 GiB1
g6e.8xlarge 32256 GiB1
g6e.12xlarge 48384 GiB4
g6e.16xlarge 64512 GiB1
g6e.24xlarge 96768 GiB4
g6e.48xlarge 1921536 GiB8

Similar Servers

INSTANCEVENDORvCPUsMEMORYGPUs

g6e.4xlarge FAQs