g4dn.16xlarge by Amazon Web Services

g4dn.16xlarge is a Graphics intensive [Instance store volumes] [Network and EBS optimized] Gen4 16xlarge server offered by Amazon Web Services with 64 vCPUs, 256 GiB of memory and 900 GB of storage. The pricing starts at 0.4617 USD per hour.
64 vCPU
256 GiB Memory
900 GB Storage
1 GPU
Spare SCore
54,155
(All-cores)
1,285
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
g4dn.16xlarge
Description
Graphics intensive [Instance store volumes] [Network and EBS optimized] Gen4 16xlarge
Family
g4dn
Hw Virt
Status
active
Observed At
2026-11-11T14:49:17.748071

Availability

REGION / IDSPOTONDEMAND
Northern Virgina (US) / us-east-1
1.28484 USD/h 4.352 USD/h
Oregon (US) / us-west-2
1.534867 USD/h 4.352 USD/h
Ohio (US) / us-east-2
2.0544 USD/h 4.352 USD/h
Stockholm (SE) / eu-north-1
0.6555 USD/h 4.617 USD/h
Mumbai (IN) / ap-south-1
0.7728 USD/h 4.791 USD/h
Quebec (CA) / ca-central-1
0.89115 USD/h 4.832 USD/h
Dublin (IE) / eu-west-1
1.273267 USD/h 4.853 USD/h
Paris (FR) / eu-west-3
0.823 USD/h 5.088 USD/h
London (GB) / eu-west-2
1.0735 USD/h 5.092 USD/h
Milan (IT) / eu-south-1
0.69295 USD/h 5.095 USD/h
California (US) / us-west-1
0.68175 USD/h 5.222 USD/h
Seoul (KR) / ap-northeast-2
2.408933 USD/h 5.353 USD/h
Frankfurt (DE) / eu-central-1
1.876133 USD/h 5.44 USD/h
Sydney (AU) / ap-southeast-2
1.861567 USD/h 5.659 USD/h
Cape Town (ZA) / af-south-1
2.1419 USD/h 5.774 USD/h
Osaka (JP) / ap-northeast-3
0.6935 USD/h 5.875 USD/h
Tokyo (JP) / ap-northeast-1
2.829533 USD/h 5.875 USD/h
Singapore (SG) / ap-southeast-1
1.6454 USD/h 6.089 USD/h
Hong Kong (HK) / ap-east-1
0.6702 USD/h 6.702 USD/h
Sao Paulo (BR) / sa-east-1
0.7397 USD/h 7.397 USD/h

Processor

vCPUs
64
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
32
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
1 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
1 MiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
32 MiB
CPU L3 Cache
36 MiB
CPU L3 Cache Total
72 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, rep_good, nopl, xtopology, nonstop_tsc, cpuid, aperfmperf, tsc_known_freq, pni, pclmulqdq, 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
42.1
Scalability
65.78

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
16 GiB
Accelerator Memory Total
16 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Turing
Accelerator Model
T4
Accelerators
  • 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 GPU-accelerated instance featuring dedicated Intel Xeon processors, local NVMe storage, and high-speed networking for machine learning inference workloads.

Amazon Web Services g4dn.16xlarge is a GPU-accelerated server instance designed for graphics-intensive and machine learning workloads. Powered by an Intel Xeon 8259CL processor, it features 64 dedicated vCPUs, 256.0 GB of DDR4 memory, and a single NVIDIA Turing T4 GPU with 16 GB of VRAM. Storage is supported by a 900 GB NVMe SSD, and networking delivers a 50 Gbps baseline. While single-core CPU benchmarks are weak, multi-core performance is average, and large-block memory bandwidth is strong. The instance demonstrates top-tier performance in LLM inference prompt processing for small and medium models. This hardware profile is suited for machine learning inference, graphics rendering, and workloads requiring high network throughput and local NVMe storage.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

2.2Score
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) 5,446,150 ops/sec 1,926,573 ops/sec 2.8 50.00% 50.00% +67.00%
Redis RPS (pipeline=16, SET) 31,774,146 ops/sec 11,810,473 ops/sec 2.7 20.00% 20.00% +22.00%
PassMark Memory Mark (composite) 2,632 2,406 1.1 10.00% 10.00% +0.96%
Memory bandwidth (read, 16 MB ~ L3) 225,274 MB/sec 108,674 MB/sec 2.1 10.00% 10.00% +7.70%
PassMark single-thread CPU 1,810 Mops/s 2,365 Mops/s 0.75 10.00% 10.00% -2.80%

GPU Bandwidth and Latency

Node (all GPUs)
Node baseline directional bandwidth
5.7 GB/s
Node GPU-to-host bandwidth
6.6 GB/s
Node host-to-GPU bandwidth
6.3 GB/s
Single GPU slot
Per-GPU GPU-to-host bandwidth
6.6 GB/s
Per-GPU host-to-GPU bandwidth
6.3 GB/s
Per-GPU host-device latency
709 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: 1,104

Geekbench Multi-Core

Score: 11,290

Passmark CPU Scores

BENCHMARKSCORE
Mark
 42,565
Compression
 796,201
Encryption
 24,900
Extended Instructions
 49,819
Floating Point Maths
 97,176
Integer Maths
 181,488
Physics
 4,575
Prime Numbers
 256
Single Threaded
 1,810
String Sorting
 91,893

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2,632
Database Operations
 21,207
Memory Latency
 54
Memory Read Cached
 22,418
Memory Read Uncached
 10,575
Memory Write
 10,208

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
g4dn.xlarge 416 GiB1
g4dn.2xlarge 832 GiB1
g4dn.4xlarge 1664 GiB1
g4dn.8xlarge 32128 GiB1
g4dn.12xlarge 48192 GiB4
g4dn.metal 96384 GiB8

Similar Servers

INSTANCEVENDORvCPUsMEMORYAccelerators

g4dn.16xlarge FAQs