g6.16xlarge by Amazon Web Services

g6.16xlarge is a Graphics intensive Gen6 16xlarge server offered by Amazon Web Services with 64 vCPUs, 256 GiB of memory and 1.88 TB of storage. The pricing starts at 0.4079 USD per hour.
64 vCPU
256 GiB Memory
1.88 TB Storage
1 GPU
Spare SCore
95,679
(All-cores)
2,993
(Single-core)

Specifications #

Server Metadata #

Vendor ID
aws
Name
g6.16xlarge
Description
Graphics intensive Gen6 16xlarge
Family
Accelerated Computing
Series
g6
Hw Virt
Status
active
Observed At
2026-11-18T18:03:59.644304

Availability #

Region / IDSpotOndemand
Northern Virgina (US) / us-east-1
1.32586 USD/h
3.3968 USD/h
Ohio (US) / us-east-2
1.592367 USD/h
3.3968 USD/h
Oregon (US) / us-west-2
2.014275 USD/h
3.3968 USD/h
Aragón (ES) / eu-south-2
0.975933 USD/h
3.5791 USD/h
Stockholm (SE) / eu-north-1
0.8438 USD/h
3.6028 USD/h
Quebec (CA) / ca-central-1
3.7716 USD/h
3.7716 USD/h
Hyderabad (IN) / ap-south-2
1.3729 USD/h
4.0789 USD/h
Mumbai (IN) / ap-south-1
1.11385 USD/h
4.0789 USD/h
United Arab Emirates / me-central-1
0.9017 USD/h
4.171 USD/h
Seoul (KR) / ap-northeast-2
1.8834 USD/h
4.1768 USD/h
Frankfurt (DE) / eu-central-1
1.1077 USD/h
4.2477 USD/h
(MY) / ap-southeast-5
1.28405 USD/h
4.2789 USD/h
London (GB) / eu-west-2
1.0479 USD/h
4.3118 USD/h
Paris (FR) / eu-west-3
0.90785 USD/h
4.3118 USD/h
Sydney (AU) / ap-southeast-2
2.288333 USD/h
4.4165 USD/h
Zurich (CH) / eu-central-2
1.03305 USD/h
4.5794 USD/h
Tokyo (JP) / ap-northeast-1
2.50555 USD/h
4.9264 USD/h
Sao Paulo (BR) / sa-east-1
0.5774 USD/h
5.7739 USD/h

Processor #

vCPUs
64
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
32
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
1 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
1 MiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
16 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
128 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
32
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
1880 GB
Storage Type
nvme ssd
Storages
  • 940 GB nvme ssd
  • 940 GB nvme ssd
Compatible Storage IDs
standard, gp2, gp3, st1, sc1, io1, io2
Network
Network Speed Baseline
25 Gbps
Network Speed Max
25 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 #

An accelerated x86_64 server combining dedicated AMD EPYC processors, local NVMe storage, and NVIDIA L4 GPU capabilities for compute-intensive workloads.

Amazon Web Services g6.16xlarge is an x86_64 server featuring 64 dedicated vCPUs from an AMD EPYC 7R13 processor running at 3.4 GHz, paired with 256.0 GB of DDR4 memory. It integrates a single NVIDIA Ada Lovelace L4 GPU with 22 GB of VRAM and 1880 GB of local NVMe SSD storage. Operating on the Nitro hypervisor, the server delivers 25 Gbps baseline network bandwidth. Benchmarks show top-tier performance in LLM inference for small and medium models, alongside strong multi-core CPU and database execution. However, text generation for large 70B models is weak due to single-GPU limits. This configuration is suited for medium-scale AI inference, ray tracing, software compilation, and database workloads.

Economics #

Average Price per Region #

Prices per Zone #

Lowest Prices #

Performance #

Workload Profiles #

2.1Score
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) 5,236,957 ops/sec 1,933,252 ops/sec 2.7 50.00% 50.00% +64.00%
Redis RPS (pipeline=16, SET) 36,549,674 ops/sec 11,814,424 ops/sec 3.1 20.00% 20.00% +25.00%
PassMark Memory Mark (composite) 2,777 2,408 1.2 10.00% 10.00% +1.80%
Memory bandwidth (read, 16 MB ~ L3) 120,906 MB/sec 108,674 MB/sec 1.1 10.00% 10.00% +0.96%
PassMark single-thread CPU 2,640 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
801 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: 1,736

Geekbench Multi-Core #

Score: 16,623

Passmark CPU Scores #

BENCHMARKSCORE
Mark
60,670
Compression
897,370
Encryption
65,193
Extended Instructions
47,745
Floating Point Maths
144,669
Integer Maths
269,588
Physics
6,174
Prime Numbers
341
Single Threaded
2,640
String Sorting
119,896

Passmark Memory Scores #

BENCHMARKSCORE
Memory Mark
2,777
Database Operations
24,127
Memory Latency
67
Memory Read Cached
26,410
Memory Read Uncached
16,540
Memory Write
17,058

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
g6.12xlarge 48192 GiB4
g6.24xlarge 96384 GiB4
g6.48xlarge 192768 GiB8

Similar Servers #

INSTANCEVENDORvCPUsMEMORYAccelerators

g6.16xlarge FAQs #