g6.24xlarge by Amazon Web Services

g6.24xlarge is a Graphics intensive Gen6 24xlarge server offered by Amazon Web Services with 96 vCPUs, 384 GiB of memory and 3.76 TB of storage. The pricing starts at 1.3531 USD per hour.
96 vCPU
384 GiB Memory
3.76 TB Storage
4 GPU
Spare SCore
143,501
(All-cores)
2,994
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
g6.24xlarge
Description
Graphics intensive Gen6 24xlarge
Family
g6
Hw Virt
Status
active
Observed At
2026-09-12T15:17:44.804983

Availability

REGION / IDSPOTONDEMAND
Northern Virgina (US) / us-east-1
4.33734 USD/h 6.6752 USD/h
Oregon (US) / us-west-2
2.9485 USD/h 6.6752 USD/h
Ohio (US) / us-east-2
3.5156 USD/h 6.6752 USD/h
Aragón (ES) / eu-south-2
1.8284 USD/h 7.0335 USD/h
Stockholm (SE) / eu-north-1
2.0267 USD/h 7.08 USD/h
Quebec (CA) / ca-central-1
7.4117 USD/h 7.4117 USD/h
Hyderabad (IN) / ap-south-2
1.5368 USD/h 8.0155 USD/h
Mumbai (IN) / ap-south-1
4.6667 USD/h 8.0155 USD/h
United Arab Emirates / me-central-1
3.3555 USD/h 8.1967 USD/h
Seoul (KR) / ap-northeast-2
3.9304 USD/h 8.208 USD/h
Frankfurt (DE) / eu-central-1
3.089467 USD/h 8.3473 USD/h
(MY) / ap-southeast-5
1.54255 USD/h 8.4087 USD/h
Paris (FR) / eu-west-3
2.6677 USD/h 8.4734 USD/h
London (GB) / eu-west-2
4.961833 USD/h 8.4734 USD/h
Sydney (AU) / ap-southeast-2
8.581433 USD/h 8.6791 USD/h
Zurich (CH) / eu-central-2
2.79135 USD/h 8.9992 USD/h
Tokyo (JP) / ap-northeast-1
4.44635 USD/h 9.681 USD/h
Sao Paulo (BR) / sa-east-1
2.6361 USD/h 11.3465 USD/h

Processor

vCPUs
96
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
48
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
2 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
2 MiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
24 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
192 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, monitor, 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, perfctr_core, 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
47.9
Scalability
99.79

System Resources and Accelerators

MEMORY
Memory Amount
384 GiB
Memory Amount Actual
384 GiB
Memory Generation
DDR4
Memory Speed
3200 Mhz
GPU
GPU Count
4
GPU Memory Min
22 GiB
GPU Memory Total
89 GiB
GPU Manufacturer
NVIDIA
GPU Family
Ada Lovelace
GPU Model
L4
GPUs
  • 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
50 Gbps
Network Speed Max
50 Gbps
Network Storage Speed Baseline
30 Gbps
Network Storage Speed Max
30 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 dedicated AMD EPYC processors for demanding machine learning inference.

GPU AcceleratedCompute OptimizedStorage & Database

Amazon Web Services g6.24xlarge is a GPU-accelerated server instance designed for graphics-intensive and machine learning workloads. Powered by 96 vCPUs from dedicated AMD EPYC 7R13 processors running at 3.4 GHz, it features 384.0 GB of DDR4 memory and four NVIDIA L4 Ada Lovelace GPUs with 89 GB of total VRAM. Local storage is provided by a 3760 GB NVMe SSD, and network connectivity features a 50 Gbps baseline bandwidth. Benchmarks show top-tier multi-core CPU performance and exceptional LLM inference speeds for prompt processing and text generation. This hardware configuration is highly optimized for large-scale AI inference, ray tracing, image processing, and database operations.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

2.63Score
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) 6,886,807 ops/sec 1,917,397 ops/sec 3.59 50.00% 50.00% +89.50%
Redis RPS (pipeline=16, SET) 47,904,926 ops/sec 11,681,410 ops/sec 4.1 20.00% 20.00% +32.60%
PassMark Memory Mark (composite) 2,865 2,418 1.18 10.00% 10.00% +1.67%
Memory bandwidth (read, 16 MB ~ L3) 129,042 MB/sec 108,140 MB/sec 1.19 10.00% 10.00% +1.75%
PassMark single-thread CPU 2,646 Mops/s 2,365 Mops/s 1.12 10.00% 10.00% +1.14%

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 1,677

Geekbench Multi-Core

Score: 17,481

Passmark CPU Scores

BENCHMARKSCORE
Mark
 76614
Compression
 1301658
Encryption
 95981
Extended Instructions
 66453
Floating Point Maths
 216378
Integer Maths
 407745
Physics
 7417
Prime Numbers
 495
Single Threaded
 2646
String Sorting
 167002

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2865
Database Operations
 25919
Memory Latency
 66
Memory Read Cached
 26364
Memory Read Uncached
 17316
Memory Write
 17732

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
g6.xlarge 416 GiB1
g6.2xlarge 832 GiB1
g6.4xlarge 1664 GiB1
g6.8xlarge 32128 GiB1
g6.12xlarge 48192 GiB4
g6.16xlarge 64256 GiB1
g6.48xlarge 192768 GiB8

Similar Servers

INSTANCEVENDORvCPUsMEMORYGPUs

g6.24xlarge FAQs