g6.12xlarge by Amazon Web Services

g6.12xlarge is a Graphics intensive Gen6 12xlarge server offered by Amazon Web Services with 48 vCPUs, 192 GiB of memory and 3.76 TB of storage. The pricing starts at 0.5526 USD per hour.
48 vCPU
192 GiB Memory
3.76 TB Storage
4 GPU
Spare SCore
71,802
(All-cores)
2,990
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
g6.12xlarge
Description
Graphics intensive Gen6 12xlarge
Family
g6
Hw Virt
Average Time To Start
702.5
Status
active
Observed At
2026-10-19T17:02:48.407875

Availability

REGION / IDSPOTONDEMAND
Northern Virgina (US) / us-east-1
3.27162 USD/h 4.6016 USD/h
Ohio (US) / us-east-2
2.491 USD/h 4.6016 USD/h
Oregon (US) / us-west-2
3.53255 USD/h 4.6016 USD/h
Aragón (ES) / eu-south-2
1.556467 USD/h 4.8486 USD/h
Stockholm (SE) / eu-north-1
1.4034 USD/h 4.8806 USD/h
Quebec (CA) / ca-central-1
5.1093 USD/h 5.1093 USD/h
Hyderabad (IN) / ap-south-2
2.6024 USD/h 5.5256 USD/h
Mumbai (IN) / ap-south-1
2.5192 USD/h 5.5256 USD/h
United Arab Emirates / me-central-1
2.3132 USD/h 5.6505 USD/h
Seoul (KR) / ap-northeast-2
2.8612 USD/h 5.6582 USD/h
Frankfurt (DE) / eu-central-1
3.003 USD/h 5.7543 USD/h
(MY) / ap-southeast-5
1.96515 USD/h 5.7966 USD/h
Paris (FR) / eu-west-3
1.8884 USD/h 5.8412 USD/h
London (GB) / eu-west-2
2.7702 USD/h 5.8412 USD/h
Sydney (AU) / ap-southeast-2
3.285867 USD/h 5.983 USD/h
Zurich (CH) / eu-central-2
1.85495 USD/h 6.2037 USD/h
Tokyo (JP) / ap-northeast-1
3.08375 USD/h 6.6737 USD/h
Sao Paulo (BR) / sa-east-1
1.0942 USD/h 7.8218 USD/h

Processor

vCPUs
48
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
24
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
768 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
768 KiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
12 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
96 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
24
Scalability
50

System Resources and Accelerators

MEMORY
Memory Amount
192 GiB
Memory Amount Actual
192 GiB
Memory Generation
DDR4
Memory Speed
3200 Mhz
ACCELERATORS
Accelerator Count
4
Accelerator Memory Min
22 GiB
Accelerator Memory Total
89 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)
  • NVIDIA Ada Lovelace NVIDIA L4 (Memory amount: 23034, Firmware version: 590.48.01, BIOS version: 95.04.65.00.37, Clock rate: 2040)
  • NVIDIA Ada Lovelace NVIDIA L4 (Memory amount: 23034, Firmware version: 590.48.01, BIOS version: 95.04.65.00.37, Clock rate: 2040)
  • 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
3760 GB
Storage Type
nvme ssd
Storages
  • 940 GB nvme ssd
  • 940 GB nvme ssd
  • 940 GB nvme ssd
  • 940 GB nvme ssd
NETWORK
Network Speed Baseline
40 Gbps
Network Speed Max
40 Gbps
Network Storage Speed Baseline
20 Gbps
Network Storage Speed Max
20 Gbps
Inbound Traffic
0 GB/month
Outbound Traffic
0 GB/month
IPv4
0

CPU and System Topology

Server Description

A high-density GPU instance featuring four NVIDIA L4 accelerators and local NVMe storage for advanced machine learning inference and graphics rendering.

GPU AcceleratedCompute OptimizedStorage & Database

Amazon Web Services g6.12xlarge is a GPU-accelerated server instance powered by an AMD EPYC 7R13 processor with 48 dedicated vCPUs and 192.0 GB of DDR4 memory. It features four NVIDIA L4 GPUs based on the Ada Lovelace architecture, delivering a total of 89 GB of VRAM, alongside 3760 GB of local NVMe SSD storage and 40 Gbps baseline network bandwidth. Benchmarks show strong CPU and graphics performance, with top-tier results in large language model inference for prompt processing and text generation. The server provides high resource density, making it a cost-efficient choice for parallelized workloads without the expense of top-tier enterprise accelerators. It is highly suited for machine learning inference, ray tracing, image processing, and media transcoding workloads.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

1.8Score
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) 4,139,757 ops/sec 1,917,050 ops/sec 2.2 50.00% 50.00% +48.00%
Redis RPS (pipeline=16, SET) 29,871,345 ops/sec 11,661,818 ops/sec 2.5 20.00% 20.00% +20.00%
PassMark Memory Mark (composite) 2,566 2,417 1.1 10.00% 10.00% +0.96%
Memory bandwidth (read, 16 MB ~ L3) 108,596 MB/sec 108,361 MB/sec 1 10.00% 10.00% 0.00%
PassMark single-thread CPU 2,643 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
44.3 GB/s
Node GPU-to-host bandwidth
52.9 GB/s
Node host-to-GPU bandwidth
53.9 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
811 ns
Benchmark Environment
Driver Version
 535.183.01
CUDA Runtime Version
 12.6
nvbandwidth Version
 v0.5
GPU Count
 4
P2P Supported
No
Efficiency
SM/CE copy efficiency
1.00

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 1,748

Geekbench Multi-Core

Score: 15,905

Passmark CPU Scores

BENCHMARKSCORE
Mark
 55,482
Compression
 828,117
Encryption
 56,908
Extended Instructions
 43,721
Floating Point Maths
 121,171
Integer Maths
 220,865
Physics
 5,338
Prime Numbers
 285
Single Threaded
 2,643
String Sorting
 112,261

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2,566
Database Operations
 20,385
Memory Latency
 77
Memory Read Cached
 26,407
Memory Read Uncached
 16,908
Memory Write
 17,390

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
g6.8xlarge 32128 GiB1
g6.16xlarge 64256 GiB1
g6.24xlarge 96384 GiB4
g6.48xlarge 192768 GiB8

Similar Servers

INSTANCEVENDORvCPUsMEMORYAccelerators

g6.12xlarge FAQs