g6e.8xlarge by Amazon Web Services

g6e.8xlarge is a Graphics intensive [Extra storage or memory] Gen6 8xlarge server offered by Amazon Web Services with 32 vCPUs, 256 GiB of memory and 900 GB of storage. The pricing starts at 0.7829 USD per hour.
32 vCPU
256 GiB Memory
900 GB Storage
1 GPU
Spare SCore
47,887
(All-cores)
2,993
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
g6e.8xlarge
Description
Graphics intensive [Extra storage or memory] Gen6 8xlarge
Family
g6e
Hw Virt
Status
active
Observed At
2026-10-30T04:38:10.394437

Availability

REGION / IDSPOTONDEMAND
Northern Virgina (US) / us-east-1
2.32075 USD/h 4.5286 USD/h
Oregon (US) / us-west-2
2.97565 USD/h 4.5286 USD/h
Ohio (US) / us-east-2
2.9007 USD/h 4.5286 USD/h
Aragón (ES) / eu-south-2
2.07285 USD/h 4.7719 USD/h
Stockholm (SE) / eu-north-1
1.59625 USD/h 4.8035 USD/h
Hyderabad (IN) / ap-south-2
1.14255 USD/h 5.4386 USD/h
Mumbai (IN) / ap-south-1
2.43065 USD/h 5.4386 USD/h
United Arab Emirates / me-central-1
2.2743 USD/h 5.5555 USD/h
Seoul (KR) / ap-northeast-2
2.69875 USD/h 5.5676 USD/h
Frankfurt (DE) / eu-central-1
3.176133 USD/h 5.6625 USD/h
Osaka (JP) / ap-northeast-3
2.0479 USD/h 6.5678 USD/h
Tokyo (JP) / ap-northeast-1
3.12975 USD/h 6.5678 USD/h

Processor

vCPUs
32
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
16
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
512 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
512 KiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
8 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
64 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
16
Scalability
50

System Resources and Accelerators

MEMORY
Memory Amount
256 GiB
Memory Amount Actual
256 GiB
Memory Generation
DDR4
Memory Speed
3200 Mhz
ACCELERATORS
Accelerator Count
1
Accelerator Memory Min
45 GiB
Accelerator Memory Total
45 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)
STORAGE
Storage Size
900 GB
Storage Type
nvme ssd
Storages
  • 450 GB nvme ssd
  • 450 GB nvme ssd
NETWORK
Network Speed Baseline
25 Gbps
Network Speed Max
25 Gbps
Network Storage Speed Baseline
16 Gbps
Network Storage Speed Max
16 Gbps
Inbound Traffic
0 GB/month
Outbound Traffic
0 GB/month
IPv4
0

CPU and System Topology

Server Description

A GPU-accelerated server featuring an NVIDIA L40S GPU and local NVMe storage, optimized for high-throughput large language model inference.

GPU AcceleratedMemory OptimizedStorage & Database

Amazon Web Services g6e.8xlarge is a graphics-intensive virtual server built on the Nitro hypervisor. It features a 32-vCPU AMD EPYC 7R13 processor running at 3.4 GHz, 256.0 GB of DDR4 memory, and a single NVIDIA L40S GPU with 45 GB of VRAM. Local storage is provided by a 900 GB NVMe SSD, complemented by a 25 Gbps baseline network bandwidth. In benchmark testing, the server demonstrates top-tier performance in large language model inference, processing prompts at up to 13,452.05 tokens per second on small models and 874.26 tokens per second on 70B models. Single-core CPU and encryption benchmarks are strong, while multi-core and memory bandwidth metrics remain average. This hardware profile is optimized for machine learning inference, graphics rendering, and database workloads requiring dedicated GPU acceleration and local high-speed storage.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

1.4Score
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) 2,797,681 ops/sec 1,919,289 ops/sec 1.5 50.00% 50.00% +22.00%
Redis RPS (pipeline=16, SET) 20,053,334 ops/sec 11,728,058 ops/sec 1.7 20.00% 20.00% +11.00%
PassMark Memory Mark (composite) 2,771 2,416 1.2 10.00% 10.00% +1.80%
Memory bandwidth (read, 16 MB ~ L3) 80,835 MB/sec 108,466 MB/sec 0.74 10.00% 10.00% -3.00%
PassMark single-thread CPU 2,635 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
11.0 GB/s
Node GPU-to-host bandwidth
13.2 GB/s
Node host-to-GPU bandwidth
13.5 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
810 ns
Benchmark Environment
Driver Version
 535.183.01
CUDA Version (driver)
 12.6
nvbandwidth Version
 v0.5
GPU Count
 1
P2P Supported
No
Efficiency
SM/CE copy efficiency
1.00

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 1,681

Geekbench Multi-Core

Score: 14,031

Passmark CPU Scores

BENCHMARKSCORE
Mark
 41,864
Compression
 561,206
Encryption
 37,991
Extended Instructions
 33,163
Floating Point Maths
 80,815
Integer Maths
 147,250
Physics
 3,875
Prime Numbers
 195
Single Threaded
 2,635
String Sorting
 75,568

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2,771
Database Operations
 14,178
Memory Latency
 66
Memory Read Cached
 26,393
Memory Read Uncached
 17,067
Memory Write
 17,837

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.12xlarge 48384 GiB4
g6e.16xlarge 64512 GiB1
g6e.24xlarge 96768 GiB4
g6e.48xlarge 1921536 GiB8

Similar Servers

INSTANCEVENDORvCPUsMEMORYAccelerators

g6e.8xlarge FAQs