g6.2xlarge by Amazon Web Services

g6.2xlarge is a Graphics intensive Gen6 2xlarge server offered by Amazon Web Services with 8 vCPUs, 32 GiB of memory and 450 GB of storage. The pricing starts at 0.14 USD per hour.
8 vCPU
32 GiB Memory
450 GB Storage
1 GPU
Spare SCore
11,969
(All-cores)
2,993
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
g6.2xlarge
Description
Graphics intensive Gen6 2xlarge
Family
g6
Hw Virt
Status
active
Observed At
2026-10-19T17:02:48.407623

Availability

REGION / IDSPOTONDEMAND
Oregon (US) / us-west-2
0.768675 USD/h 0.9776 USD/h
Ohio (US) / us-east-2
0.4823 USD/h 0.9776 USD/h
Northern Virgina (US) / us-east-1
0.92418 USD/h 0.9776 USD/h
Aragón (ES) / eu-south-2
0.306933 USD/h 1.0301 USD/h
Stockholm (SE) / eu-north-1
0.14695 USD/h 1.0369 USD/h
Quebec (CA) / ca-central-1
0.923333 USD/h 1.0855 USD/h
Hyderabad (IN) / ap-south-2
0.61165 USD/h 1.1739 USD/h
Mumbai (IN) / ap-south-1
0.58135 USD/h 1.1739 USD/h
United Arab Emirates / me-central-1
0.4914 USD/h 1.2004 USD/h
Seoul (KR) / ap-northeast-2
0.554333 USD/h 1.2021 USD/h
Frankfurt (DE) / eu-central-1
0.7727 USD/h 1.2225 USD/h
(MY) / ap-southeast-5
0.57485 USD/h 1.2315 USD/h
London (GB) / eu-west-2
0.333667 USD/h 1.2409 USD/h
Paris (FR) / eu-west-3
0.39105 USD/h 1.2409 USD/h
Sydney (AU) / ap-southeast-2
0.788433 USD/h 1.2711 USD/h
Zurich (CH) / eu-central-2
0.40995 USD/h 1.318 USD/h
Tokyo (JP) / ap-northeast-1
0.68605 USD/h 1.4178 USD/h
Sao Paulo (BR) / sa-east-1
0.30275 USD/h 1.6617 USD/h

Processor

vCPUs
8
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
4
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
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, 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
4
Scalability
50

System Resources and Accelerators

MEMORY
Memory Amount
32 GiB
Memory Amount Actual
32 GiB
Memory Generation
DDR4
Memory Speed
3200 Mhz
ACCELERATORS
Accelerator Count
1
Accelerator Memory Min
22 GiB
Accelerator Memory Total
22 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Ada Lovelace
Accelerator Model
L4
Accelerators
  • NVIDIA Ada Lovelace NVIDIA L4 (Memory amount: 23034, Firmware version: 590.48.01, BIOS version: 95.04.65.00.37, Clock rate: 2040)
STORAGE
Storage Size
450 GB
Storage Type
nvme ssd
Storages
  • 450 GB nvme ssd
NETWORK
Network Speed Baseline
5 Gbps
Network Speed Max
10 Gbps
Network Storage Speed Baseline
2 Gbps
Network Storage Speed Max
5 Gbps
Inbound Traffic
0 GB/month
Outbound Traffic
0 GB/month
IPv4
0

CPU and System Topology

Server Description

An accelerator-equipped virtual server featuring dedicated AMD EPYC cores, local NVMe storage, and an NVIDIA L4 GPU for specialized workloads.

GPU AcceleratedStorage & DatabaseGeneral Purpose

Amazon Web Services g6.2xlarge is an x86_64 virtual server built on the Nitro hypervisor, featuring 8 vCPUs from an AMD EPYC 7R13 processor running at 3.4 GHz, 32.0 GB of DDR4 RAM, and 450 GB of local NVMe SSD storage. It includes a single NVIDIA Ada Lovelace L4 GPU with 22 GB of VRAM. Benchmarks indicate top-tier performance for LLM inference on small and medium models, alongside strong single-core CPU performance. However, uncached memory bandwidth for large blocks is a bottleneck, scoring in the bottom 25%. This instance provides a qualitatively cost-efficient profile for graphics-intensive tasks, ray tracing, and moderate machine learning inference workloads that benefit from dedicated GPU acceleration and local NVMe storage without requiring high baseline network speeds.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

0.48Score
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) 698,655 ops/sec 1,917,050 ops/sec 0.37 50.00% 50.00% -39.00%
Redis RPS (pipeline=16, SET) 5,285,837 ops/sec 11,661,818 ops/sec 0.44 20.00% 20.00% -15.00%
PassMark Memory Mark (composite) 2,459 2,417 1 10.00% 10.00% 0.00%
Memory bandwidth (read, 16 MB ~ L3) 48,873 MB/sec 108,361 MB/sec 0.45 10.00% 10.00% -7.70%
PassMark single-thread CPU 2,614 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
802 ns
Benchmark Environment
Driver Version
 535.183.01
CUDA Runtime Version
 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: 1,744

Geekbench Multi-Core

Score: 6,700

Passmark CPU Scores

BENCHMARKSCORE
Mark
 13,090
Compression
 142,615
Encryption
 9,562
Extended Instructions
 8,137
Floating Point Maths
 20,266
Integer Maths
 36,803
Physics
 1,428
Prime Numbers
 81
Single Threaded
 2,614
String Sorting
 19,696

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2,459
Database Operations
 3,721
Memory Latency
 67
Memory Read Cached
 26,437
Memory Read Uncached
 16,888
Memory Write
 17,514

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
g6.xlarge 416 GiB1
g6.4xlarge 1664 GiB1
g6.8xlarge 32128 GiB1
g6.12xlarge 48192 GiB4
g6.16xlarge 64256 GiB1
g6.24xlarge 96384 GiB4
g6.48xlarge 192768 GiB8

Similar Servers

INSTANCEVENDORvCPUsMEMORYAccelerators

g6.2xlarge FAQs