g4dn.12xlarge by Amazon Web Services

g4dn.12xlarge is a Graphics intensive [Instance store volumes] [Network and EBS optimized] Gen4 12xlarge server offered by Amazon Web Services with 48 vCPUs, 192 GiB of memory and 900 GB of storage. The pricing starts at 0.8693 USD per hour.
48 vCPU
192 GiB Memory
900 GB Storage
4 GPU
Spare SCore
40,680
(All-cores)
1,385
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
g4dn.12xlarge
Description
Graphics intensive [Instance store volumes] [Network and EBS optimized] Gen4 12xlarge
Family
g4dn
Hw Virt
Status
active
Observed At
2026-10-06T14:38:19.262902

Availability

REGION / IDSPOTONDEMAND
Northern Virgina (US) / us-east-1
1.52518 USD/h 3.912 USD/h
Oregon (US) / us-west-2
1.560767 USD/h 3.912 USD/h
Ohio (US) / us-east-2
1.914733 USD/h 3.912 USD/h
Stockholm (SE) / eu-north-1
1.300467 USD/h 4.15 USD/h
Mumbai (IN) / ap-south-1
1.928633 USD/h 4.306 USD/h
Quebec (CA) / ca-central-1
1.70705 USD/h 4.343 USD/h
Dublin (IE) / eu-west-1
2.014067 USD/h 4.362 USD/h
Paris (FR) / eu-west-3
1.440367 USD/h 4.574 USD/h
London (GB) / eu-west-2
1.7439 USD/h 4.577 USD/h
Milan (IT) / eu-south-1
2.4686 USD/h 4.58 USD/h
California (US) / us-west-1
2.35315 USD/h 4.694 USD/h
Seoul (KR) / ap-northeast-2
2.737 USD/h 4.812 USD/h
Frankfurt (DE) / eu-central-1
2.0096 USD/h 4.89 USD/h
Sydney (AU) / ap-southeast-2
2.461367 USD/h 5.087 USD/h
Cape Town (ZA) / af-south-1
1.26075 USD/h 5.19 USD/h
Osaka (JP) / ap-northeast-3
1.45345 USD/h 5.281 USD/h
Tokyo (JP) / ap-northeast-1
2.6945 USD/h 5.281 USD/h
Singapore (SG) / ap-southeast-1
1.9094 USD/h 5.474 USD/h
Hong Kong (HK) / ap-east-1
3.033667 USD/h 6.024 USD/h
Sao Paulo (BR) / sa-east-1
1.744933 USD/h 6.649 USD/h

Processor

vCPUs
48
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
24
CPU Speed
2.5 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
8259CL
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
1 MiB
CPU L2 Cache Total
24 MiB
CPU L3 Cache
36 MiB
CPU L3 Cache Total
36 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, ss, ht, syscall, nx, pdpe1gb, rdtscp, lm, constant_tsc, arch_perfmon, rep_good, nopl, xtopology, nonstop_tsc, cpuid, aperfmperf, tsc_known_freq, pni, pclmulqdq, monitor, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, tsc_deadline_timer, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, pti, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, erms, invpcid, mpx, avx512f, avx512dq, rdseed, adx, smap, clflushopt, clwb, avx512cd, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, ida, arat, pku, ospke, avx512_vnni
Ecpus
29.4
Scalability
61.25

System Resources and Accelerators

MEMORY
Memory Amount
192 GiB
Memory Amount Actual
192 GiB
Memory Generation
DDR4
Memory Speed
3200 Mhz
GPU
GPU Count
4
GPU Memory Min
16 GiB
GPU Memory Total
64 GiB
GPU Manufacturer
NVIDIA
GPU Family
Turing
GPU Model
T4
GPUs
  • NVIDIA Turing Tesla T4 (Memory amount: 15360, Firmware version: 590.48.01, BIOS version: 90.04.96.00.02, Clock rate: 1590)
  • NVIDIA Turing Tesla T4 (Memory amount: 15360, Firmware version: 590.48.01, BIOS version: 90.04.96.00.02, Clock rate: 1590)
  • NVIDIA Turing Tesla T4 (Memory amount: 15360, Firmware version: 590.48.01, BIOS version: 90.04.96.00.02, Clock rate: 1590)
  • NVIDIA Turing Tesla T4 (Memory amount: 15360, Firmware version: 590.48.01, BIOS version: 90.04.96.00.02, Clock rate: 1590)
STORAGE
Storage Size
900 GB
Storage Type
nvme ssd
Storages
  • 900 GB nvme ssd
NETWORK
Network Speed Baseline
50 Gbps
Network Speed Max
50 Gbps
Network Storage Speed Baseline
9.5 Gbps
Network Storage Speed Max
9.5 Gbps
Inbound Traffic
0 GB/month
Outbound Traffic
0 GB/month
IPv4
0

CPU and System Topology

Server Description

A multi-GPU accelerated platform featuring four NVIDIA T4 GPUs and local NVMe storage optimized for parallel machine learning inference and graphics rendering.

GPU AcceleratedCompute OptimizedStorage & Database

Amazon Web Services g4dn.12xlarge is a GPU-accelerated instance designed for graphics-intensive and machine learning workloads. Powered by the AWS Nitro hypervisor, it features 48 vCPUs from an Intel Xeon 8259CL processor, 192.0 GB of DDR4 memory, and four NVIDIA Turing T4 GPUs providing 64 GB of total VRAM. Storage is supported by a 900 GB local NVMe SSD, and network throughput reaches a baseline of 50 Gbps. Benchmark results show a tradeoff: single-core CPU performance is weak, falling into the bottom 25%, whereas multi-core CPU and memory bandwidth perform at an average level. Notably, LLM inference prompt processing ranks in the top 10% across various model sizes. This instance is highly efficient for workloads such as multi-GPU machine learning inference, graphics rendering, video transcoding, and distributed database operations.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

1.6Score
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) 3,984,859 ops/sec 1,916,704 ops/sec 2.1 50.00% 50.00% +45.00%
Redis RPS (pipeline=16, SET) 23,241,554 ops/sec 11,642,227 ops/sec 1.9 20.00% 20.00% +14.00%
PassMark Memory Mark (composite) 2,650 2,417 1.1 10.00% 10.00% +0.96%
Memory bandwidth (read, 16 MB ~ L3) 112,947 MB/sec 108,361 MB/sec 1 10.00% 10.00% 0.00%
PassMark single-thread CPU 1,946 Mops/s 2,365 Mops/s 0.79 10.00% 10.00% -2.30%

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 1,248

Geekbench Multi-Core

Score: 10,986

Passmark CPU Scores

BENCHMARKSCORE
Mark
 34629
Compression
 598622
Encryption
 18582
Extended Instructions
 37023
Floating Point Maths
 73015
Integer Maths
 136423
Physics
 2506
Prime Numbers
 166
Single Threaded
 1946
String Sorting
 69046

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2650
Database Operations
 15531
Memory Latency
 53
Memory Read Cached
 23650
Memory Read Uncached
 10576
Memory Write
 10112

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
g4dn.xlarge 416 GiB1
g4dn.2xlarge 832 GiB1
g4dn.4xlarge 1664 GiB1
g4dn.8xlarge 32128 GiB1
g4dn.16xlarge 64256 GiB1
g4dn.metal 96384 GiB8

Similar Servers

INSTANCEVENDORvCPUsMEMORYGPUs

g4dn.12xlarge FAQs