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 0.29 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
2026-10-19T17:02:48.396391

Availability

REGION / IDSPOTONDEMAND
Northern Virgina (US) / us-east-1
0.87684 USD/h 2.0144 USD/h
Oregon (US) / us-west-2
0.874625 USD/h 2.0144 USD/h
Ohio (US) / us-east-2
0.9927 USD/h 2.0144 USD/h
Aragón (ES) / eu-south-2
0.4011 USD/h 2.1225 USD/h
Stockholm (SE) / eu-north-1
0.4052 USD/h 2.1366 USD/h
Quebec (CA) / ca-central-1
1.8589 USD/h 2.2367 USD/h
Hyderabad (IN) / ap-south-2
1.164 USD/h 2.4189 USD/h
Mumbai (IN) / ap-south-1
0.8177 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
1.131967 USD/h 2.4769 USD/h
Frankfurt (DE) / eu-central-1
0.9134 USD/h 2.519 USD/h
(MY) / ap-southeast-5
0.83415 USD/h 2.5375 USD/h
London (GB) / eu-west-2
0.9056 USD/h 2.557 USD/h
Paris (FR) / eu-west-3
0.81795 USD/h 2.557 USD/h
Sydney (AU) / ap-southeast-2
0.8847 USD/h 2.6191 USD/h
Zurich (CH) / eu-central-2
0.59475 USD/h 2.7157 USD/h
Tokyo (JP) / ap-northeast-1
1.45965 USD/h 2.9215 USD/h
Sao Paulo (BR) / sa-east-1
0.41135 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
50

System Resources and Accelerators

MEMORY
Memory Amount
128 GiB
Memory Amount Actual
128 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
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

1.3Score
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 1,917,050 ops/sec 1.5 50.00% 50.00% +22.00%
Redis RPS (pipeline=16, SET) 20,106,773 ops/sec 11,661,818 ops/sec 1.7 20.00% 20.00% +11.00%
PassMark Memory Mark (composite) 2,729 2,417 1.1 10.00% 10.00% +0.96%
Memory bandwidth (read, 16 MB ~ L3) 77,569 MB/sec 108,361 MB/sec 0.71 10.00% 10.00% -3.40%
PassMark single-thread CPU 2,644 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
13.4 GB/s
Single GPU slot
Per-GPU GPU-to-host bandwidth
13.2 GB/s
Per-GPU host-to-GPU bandwidth
13.4 GB/s
Per-GPU host-device latency
781 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: 1,738

Geekbench Multi-Core

Score: 14,166

Passmark CPU Scores

BENCHMARKSCORE
Mark
 41,941
Compression
 562,501
Encryption
 37,937
Extended Instructions
 32,765
Floating Point Maths
 80,799
Integer Maths
 147,218
Physics
 4,036
Prime Numbers
 198
Single Threaded
 2,644
String Sorting
 75,597

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2,729
Database Operations
 14,154
Memory Latency
 67
Memory Read Cached
 26,430
Memory Read Uncached
 17,169
Memory Write
 17,738

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

Similar Servers

INSTANCEVENDORvCPUsMEMORYAccelerators

g6.8xlarge FAQs