g6e.12xlarge by Amazon Web Services

g6e.12xlarge is a Graphics intensive [Extra storage or memory] Gen6 12xlarge server offered by Amazon Web Services with 48 vCPUs, 384 GiB of memory and 3.8 TB of storage. The pricing starts at 2.1635 USD per hour.
48 vCPU
384 GiB Memory
3.8 TB Storage
4 GPU
Spare SCore
71,794
(All-cores)
2,992
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
g6e.12xlarge
Description
Graphics intensive [Extra storage or memory] Gen6 12xlarge
Family
g6e
Hw Virt
Status
active
Observed At
2026-11-01T08:36:12.108715

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
5.391133 USD/h 10.4926 USD/h
Northern Virgina (US) / us-east-1
7.349525 USD/h 10.4926 USD/h
Oregon (US) / us-west-2
10.188175 USD/h 10.4926 USD/h
Aragón (ES) / eu-south-2
9.5365 USD/h 11.0564 USD/h
Stockholm (SE) / eu-north-1
9.1107 USD/h 11.1297 USD/h
Hyderabad (IN) / ap-south-2
3.19115 USD/h 12.6013 USD/h
Mumbai (IN) / ap-south-1
5.6307 USD/h 12.6013 USD/h
United Arab Emirates / me-central-1
5.2695 USD/h 12.8719 USD/h
Seoul (KR) / ap-northeast-2
6.1506 USD/h 12.9001 USD/h
Frankfurt (DE) / eu-central-1
13.12 USD/h 13.12 USD/h
Osaka (JP) / ap-northeast-3
3.845 USD/h 15.2174 USD/h
Tokyo (JP) / ap-northeast-1
7.55605 USD/h 15.2174 USD/h

Processor

vCPUs
48
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
24
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
768 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
768 KiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
12 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
96 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, monitor, 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, perfctr_core, 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
24
Scalability
50

System Resources and Accelerators

MEMORY
Memory Amount
384 GiB
Memory Amount Actual
384 GiB
Memory Generation
DDR4
Memory Speed
3200 Mhz
ACCELERATORS
Accelerator Count
4
Accelerator Memory Min
45 GiB
Accelerator Memory Total
179 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Ada Lovelace
Accelerator Model
L40S
Accelerators
  • NVIDIA Ada Lovelace NVIDIA L40S (Memory amount: 46068, Firmware version: 590.48.01, BIOS version: 95.02.66.00.15, Clock rate: 2520)
  • NVIDIA Ada Lovelace NVIDIA L40S (Memory amount: 46068, Firmware version: 590.48.01, BIOS version: 95.02.66.00.15, Clock rate: 2520)
  • NVIDIA Ada Lovelace NVIDIA L40S (Memory amount: 46068, Firmware version: 590.48.01, BIOS version: 95.02.66.00.15, Clock rate: 2520)
  • 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
3800 GB
Storage Type
nvme ssd
Storages
  • 1900 GB nvme ssd
  • 1900 GB nvme ssd
NETWORK
Network Speed Baseline
100 Gbps
Network Speed Max
100 Gbps
Network Storage Speed Baseline
20 Gbps
Network Storage Speed Max
20 Gbps
Inbound Traffic
0 GB/month
Outbound Traffic
0 GB/month
IPv4
0

CPU and System Topology

Server Description

A GPU-accelerated platform featuring four NVIDIA L40S GPUs, local NVMe storage, and 100 Gbps networking for demanding machine learning workloads.

GPU AcceleratedCompute OptimizedStorage & Database

Amazon Web Services g6e.12xlarge is a graphics-intensive server instance built on the Nitro hypervisor. It features 48 vCPUs powered by an AMD EPYC 7R13 processor running at 3.4 GHz, paired with 384.0 GB of DDR4 memory. Acceleration is driven by four NVIDIA L40S Ada Lovelace GPUs with 179 GB of total VRAM. Storage is provided by a 3800 GB local NVMe SSD, complemented by a 100 Gbps baseline network bandwidth. In benchmark evaluations, the instance achieves top-tier performance in LLM inference across small, medium, and large models. It also registers strong scores in CPU stress tests, encryption, ray tracing, and image processing, while memory bandwidth and database operations remain in the average tier. This hardware configuration is suited for large language model deployment, graphics rendering, and cryptographic workloads requiring high-speed local storage and GPU acceleration.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

1.8Score
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) 4,159,857 ops/sec 1,918,343 ops/sec 2.2 50.00% 50.00% +48.00%
Redis RPS (pipeline=16, SET) 29,960,025 ops/sec 11,704,734 ops/sec 2.5 20.00% 20.00% +20.00%
PassMark Memory Mark (composite) 2,773 2,416 1.2 10.00% 10.00% +1.80%
Memory bandwidth (read, 16 MB ~ L3) 107,189 MB/sec 108,466 MB/sec 1 10.00% 10.00% 0.00%
PassMark single-thread CPU 2,636 Mops/s 2,365 Mops/s 1.1 10.00% 10.00% +0.96%

GPU Bandwidth and Latency

Node (all GPUs)
Node baseline directional bandwidth
44.3 GB/s
Node GPU-to-host bandwidth
52.9 GB/s
Node host-to-GPU bandwidth
53.9 GB/s
Single GPU slot
Per-GPU GPU-to-host bandwidth
13.2 GB/s
Per-GPU host-to-GPU bandwidth
13.5 GB/s
Per-GPU host-device latency
794 ns
Benchmark Environment
Driver Version
 535.183.01
CUDA Version (driver)
 12.6
nvbandwidth Version
 v0.5
GPU Count
 4
P2P Supported
No
Efficiency
SM/CE copy efficiency
1.00

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 1,688

Geekbench Multi-Core

Score: 15,708

Passmark CPU Scores

BENCHMARKSCORE
Mark
 56,073
Compression
 840,664
Encryption
 56,880
Extended Instructions
 49,176
Floating Point Maths
 121,215
Integer Maths
 220,881
Physics
 5,408
Prime Numbers
 285
Single Threaded
 2,636
String Sorting
 107,734

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2,773
Database Operations
 20,437
Memory Latency
 68
Memory Read Cached
 26,539
Memory Read Uncached
 17,026
Memory Write
 17,433

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
g6e.xlarge 432 GiB1
g6e.2xlarge 864 GiB1
g6e.4xlarge 16128 GiB1
g6e.8xlarge 32256 GiB1
g6e.16xlarge 64512 GiB1
g6e.24xlarge 96768 GiB4
g6e.48xlarge 1921536 GiB8

Similar Servers

INSTANCEVENDORvCPUsMEMORYAccelerators

g6e.12xlarge FAQs