g6.8xlarge by Amazon Web Services

g6.8xlarge is a Graphics intensive Gen6 8xlarge server offered by Amazon Web Services with 32 vCPUs, 128 GiB of memory and 900 GB of storage. The pricing starts at 0.2123 USD per hour.
32 vCPU
128 GiB Memory
900 GB Storage
1 GPU
Spare SCore
47,873
(All-cores)
2,990
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
g6.8xlarge
Description
Graphics intensive Gen6 8xlarge
Family
g6
Hw Virt
Status
active
Observed At
2026-09-04T13:58:22.548276

Availability

REGION / IDSPOTONDEMAND
Oregon (US) / us-west-2
0.868425 USD/h 2.0144 USD/h
Ohio (US) / us-east-2
0.9065 USD/h 2.0144 USD/h
Northern Virgina (US) / us-east-1
1.1451 USD/h 2.0144 USD/h
Aragón (ES) / eu-south-2
0.2123 USD/h 2.1225 USD/h
Stockholm (SE) / eu-north-1
0.52335 USD/h 2.1366 USD/h
Quebec (CA) / ca-central-1
1.019333 USD/h 2.2367 USD/h
Mumbai (IN) / ap-south-1
0.55675 USD/h 2.4189 USD/h
Hyderabad (IN) / ap-south-2
1.64285 USD/h 2.4189 USD/h
United Arab Emirates / me-central-1
1.0126 USD/h 2.4735 USD/h
Seoul (KR) / ap-northeast-2
1.1146 USD/h 2.4769 USD/h
Frankfurt (DE) / eu-central-1
0.899233 USD/h 2.519 USD/h
(MY) / ap-southeast-5
0.8057 USD/h 2.5375 USD/h
London (GB) / eu-west-2
0.764233 USD/h 2.557 USD/h
Paris (FR) / eu-west-3
0.81625 USD/h 2.557 USD/h
Sydney (AU) / ap-southeast-2
1.150233 USD/h 2.6191 USD/h
Zurich (CH) / eu-central-2
0.6927 USD/h 2.7157 USD/h
Tokyo (JP) / ap-northeast-1
1.3147 USD/h 2.9215 USD/h
Sao Paulo (BR) / sa-east-1
0.3822 USD/h 3.4241 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
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
22 GiB
GPU Memory Total
22 GiB
GPU Manufacturer
NVIDIA
GPU Family
Ada Lovelace
GPU Model
L4
GPUs
  • 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
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

An accelerated single-GPU instance featuring dedicated AMD EPYC processors and local NVMe storage for efficient machine learning inference and graphics workloads.

GPU AcceleratedGeneral Purpose

Amazon Web Services g6.8xlarge is a graphics-intensive instance featuring an x86_64 AMD EPYC 7R13 processor with 32 dedicated vCPUs, 128.0 GB of DDR4 memory, and a baseline network bandwidth of 25 Gbps. The hardware configuration includes a single NVIDIA Ada Lovelace L4 GPU with 22 GB of VRAM and 900 GB of local NVMe SSD storage. Benchmark results show strong single-core CPU and encryption performance, alongside top-tier results in LLM inference for small and medium models. The instance provides a balanced, single-GPU resource profile, making it a cost-efficient choice for machine learning inference, ray tracing, and graphics-intensive workloads.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

1.33Score
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) 2,789,099 ops/sec 1,917,397 ops/sec 1.45 50.00% 50.00% +20.40%
Redis RPS (pipeline=16, SET) 20,106,773 ops/sec 11,681,410 ops/sec 1.72 20.00% 20.00% +11.50%
PassMark Memory Mark (composite) 2,729 2,418 1.13 10.00% 10.00% +1.23%
Memory bandwidth (read, 16 MB ~ L3) 77,569 MB/sec 108,140 MB/sec 0.717 10.00% 10.00% -3.27%
PassMark single-thread CPU 2,644 Mops/s 2,365 Mops/s 1.12 10.00% 10.00% +1.14%

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 1,738

Geekbench Multi-Core

Score: 14,166

Passmark CPU Scores

BENCHMARKSCORE
Mark
 41941
Compression
 562501
Encryption
 37937
Extended Instructions
 32765
Floating Point Maths
 80799
Integer Maths
 147218
Physics
 4036
Prime Numbers
 198
Single Threaded
 2644
String Sorting
 75597

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2729
Database Operations
 14154
Memory Latency
 67
Memory Read Cached
 26430
Memory Read Uncached
 17169
Memory Write
 17738

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
g6.xlarge 416 GiB1
g6.2xlarge 832 GiB1
g6.4xlarge 1664 GiB1
g6.12xlarge 48192 GiB4
g6.16xlarge 64256 GiB1
g6.24xlarge 96384 GiB4
g6.48xlarge 192768 GiB8

Similar Servers

INSTANCEVENDORvCPUsMEMORYGPUs

g6.8xlarge FAQs