gr6.8xlarge by Amazon Web Services

gr6.8xlarge is a Graphics intensive with a one to eight ratio of vCPU to 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 0.2578 USD per hour.
32 vCPU
256 GiB Memory
900 GB Storage
1 GPU
Spare SCore
47,874
(All-cores)
2,992
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
gr6.8xlarge
Description
Graphics intensive with a one to eight ratio of vCPU to memory Gen6 8xlarge
Family
gr6
Hw Virt
Status
active
Observed At
2026-10-29T21:42:29.841357

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
0.612567 USD/h 2.4464 USD/h
Oregon (US) / us-west-2
0.97705 USD/h 2.4464 USD/h
Northern Virgina (US) / us-east-1
1.22755 USD/h 2.4464 USD/h
Aragón (ES) / eu-south-2
0.433467 USD/h 2.5777 USD/h
Stockholm (SE) / eu-north-1
0.6904 USD/h 2.5949 USD/h
Quebec (CA) / ca-central-1
1.776 USD/h 2.7163 USD/h
Mumbai (IN) / ap-south-1
0.67655 USD/h 2.9377 USD/h
Seoul (KR) / ap-northeast-2
0.40955 USD/h 3.0081 USD/h
Frankfurt (DE) / eu-central-1
0.9758 USD/h 3.0593 USD/h
(MY) / ap-southeast-5
0.6147 USD/h 3.0815 USD/h
Paris (FR) / eu-west-3
0.78365 USD/h 3.1054 USD/h
London (GB) / eu-west-2
0.55785 USD/h 3.1055 USD/h
Sydney (AU) / ap-southeast-2
0.80915 USD/h 3.1807 USD/h
Zurich (CH) / eu-central-2
0.7616 USD/h 3.4409 USD/h
Tokyo (JP) / ap-northeast-1
1.1816 USD/h 3.548 USD/h
Sao Paulo (BR) / sa-east-1
0.47115 USD/h 4.1585 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
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

A GPU-accelerated instance combining dedicated AMD EPYC processors, high-capacity DDR4 memory, and local NVMe storage for demanding inference workloads.

GPU AcceleratedMemory OptimizedStorage & Database

The Amazon Web Services gr6.8xlarge is a graphics-intensive server instance powered by an AMD EPYC 7R13 processor with 32 vCPUs and 256.0 GB of DDR4 memory, establishing a 1:8 vCPU-to-memory ratio. It features a dedicated NVIDIA L4 GPU with 22 GB of VRAM and a local 900 GB NVMe SSD. Operating on the AWS Nitro hypervisor, the instance delivers a 25 Gbps baseline network bandwidth. Benchmark results highlight top-tier performance in LLM inference for small and medium models, alongside strong single-core CPU and image processing capabilities. This hardware profile is optimized for workloads requiring a combination of GPU acceleration, high memory capacity, and local high-speed storage, such as machine learning inference, graphics rendering, and memory-intensive database operations.

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) 2,773,170 ops/sec 1,919,289 ops/sec 1.5 50.00% 50.00% +22.00%
Redis RPS (pipeline=16, SET) 19,962,308 ops/sec 11,728,058 ops/sec 1.7 20.00% 20.00% +11.00%
PassMark Memory Mark (composite) 2,795 2,416 1.2 10.00% 10.00% +1.80%
Memory bandwidth (read, 16 MB ~ L3) 78,848 MB/sec 108,466 MB/sec 0.72 10.00% 10.00% -3.20%
PassMark single-thread CPU 2,639 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
782 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: 1,733

Geekbench Multi-Core

Score: 14,220

Passmark CPU Scores

BENCHMARKSCORE
Mark
 41,924
Compression
 560,028
Encryption
 37,916
Extended Instructions
 33,099
Floating Point Maths
 80,715
Integer Maths
 147,220
Physics
 3,982
Prime Numbers
 198
Single Threaded
 2,639
String Sorting
 75,772

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2,795
Database Operations
 14,066
Memory Latency
 65
Memory Read Cached
 26,624
Memory Read Uncached
 17,307
Memory Write
 17,608

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
gr6.4xlarge 16128 GiB1

Similar Servers

INSTANCEVENDORvCPUsMEMORYAccelerators

gr6.8xlarge FAQs