g7e.48xlarge by Amazon Web Services

g7e.48xlarge is a Graphics intensive [Extra storage or memory] Gen7 48xlarge server offered by Amazon Web Services with 192 vCPUs, 2048 GiB of memory and 15.2 TB of storage. The pricing starts at 5.9385 USD per hour.
192 vCPU
2048 GiB Memory
15.2 TB Storage
8 GPU
Spare SCore
169,930
(All-cores)
2,106
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
g7e.48xlarge
Description
Graphics intensive [Extra storage or memory] Gen7 48xlarge
Family
g7e
Hw Virt
Status
active
Observed At
2026-09-20T13:00:19.718035

Availability

REGION / IDSPOTONDEMAND
Northern Virgina (US) / us-east-1
20.42895 USD/h 33.1443 USD/h
Ohio (US) / us-east-2
17.11195 USD/h 33.1443 USD/h
Oregon (US) / us-west-2
30.4239 USD/h 33.1443 USD/h
Aragón (ES) / eu-south-2
14.14655 USD/h 34.9254 USD/h
Seoul (KR) / ap-northeast-2
36.6743 USD/h 40.7492 USD/h
Stockholm (SE) / eu-north-1
24.7424 USD/h 47.8133 USD/h
Tokyo (JP) / ap-northeast-1
28.641 USD/h 48.0691 USD/h
Mumbai (IN) / ap-south-1
33.47735 USD/h 54.1351 USD/h
Frankfurt (DE) / eu-central-1
20.65395 USD/h 56.3635 USD/h
London (GB) / eu-west-2
12.9982 USD/h 57.6069 USD/h
Jakarta (ID) / ap-southeast-3
- 63.097 USD/h

Processor

vCPUs
192
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
96
CPU Speed
2.4 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
8559C
CPU L1D Cache
48 KiB
CPU L1D Cache Total
5 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
3 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
192 MiB
CPU L3 Cache
320 MiB
CPU L3 Cache Total
640 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, pdcm, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, tsc_deadline_timer, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, cpuid_fault, ssbd, ibrs, ibpb, stibp, ibrs_enhanced, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, erms, invpcid, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, avx_vnni, avx512_bf16, wbnoinvd, ida, arat, avx512vbmi, umip, pku, ospke, waitpkg, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, tme, avx512_vpopcntdq, rdpid, cldemote, movdiri, movdir64b, md_clear, serialize, amx_bf16, avx512_fp16, amx_tile, amx_int8, flush_l1d, arch_capabilities
Ecpus
80.7
Scalability
84.06

System Resources and Accelerators

MEMORY
Memory Amount
2 TB
Memory Amount Actual
2 TB
Memory Generation
DDR5
Memory Speed
5600 Mhz
GPU
GPU Count
8
GPU Memory Min
96 GiB
GPU Memory Total
768 GiB
GPU Manufacturer
NVIDIA
GPU Family
Ada Lovelace
GPU Model
RTX Pro 6000
GPUs
  • NVIDIA Blackwell NVIDIA RTX PRO 6000 Blackwell Server Edition (Memory amount: 97887, Firmware version: 590.48.01, BIOS version: 98.02.9E.00.03, Clock rate: 2430)
  • NVIDIA Blackwell NVIDIA RTX PRO 6000 Blackwell Server Edition (Memory amount: 97887, Firmware version: 590.48.01, BIOS version: 98.02.9E.00.03, Clock rate: 2430)
  • NVIDIA Blackwell NVIDIA RTX PRO 6000 Blackwell Server Edition (Memory amount: 97887, Firmware version: 590.48.01, BIOS version: 98.02.9E.00.03, Clock rate: 2430)
  • NVIDIA Blackwell NVIDIA RTX PRO 6000 Blackwell Server Edition (Memory amount: 97887, Firmware version: 590.48.01, BIOS version: 98.02.9E.00.03, Clock rate: 2430)
  • NVIDIA Blackwell NVIDIA RTX PRO 6000 Blackwell Server Edition (Memory amount: 97887, Firmware version: 590.48.01, BIOS version: 98.02.9E.00.03, Clock rate: 2430)
  • NVIDIA Blackwell NVIDIA RTX PRO 6000 Blackwell Server Edition (Memory amount: 97887, Firmware version: 590.48.01, BIOS version: 98.02.9E.00.03, Clock rate: 2430)
  • NVIDIA Blackwell NVIDIA RTX PRO 6000 Blackwell Server Edition (Memory amount: 97887, Firmware version: 590.48.01, BIOS version: 98.02.9E.00.03, Clock rate: 2430)
  • NVIDIA Blackwell NVIDIA RTX PRO 6000 Blackwell Server Edition (Memory amount: 97887, Firmware version: 590.48.01, BIOS version: 98.02.9E.00.03, Clock rate: 2430)
STORAGE
Storage Size
15200 GB
Storage Type
nvme ssd
Storages
  • 3800 GB nvme ssd
  • 3800 GB nvme ssd
  • 3800 GB nvme ssd
  • 3800 GB nvme ssd
NETWORK
Network Speed Baseline
400 Gbps
Network Speed Max
400 Gbps
Network Storage Speed Baseline
100 Gbps
Network Storage Speed Max
100 Gbps
Inbound Traffic
0 GB/month
Outbound Traffic
0 GB/month
IPv4
0

CPU and System Topology

Server Description

A high-density GPU and memory-optimized platform featuring eight professional GPUs and massive local NVMe storage for demanding AI and database workloads.

GPU AcceleratedMemory OptimizedStorage & Database

Amazon Web Services g7e.48xlarge is a high-density, graphics-intensive server instance built on the Nitro hypervisor. It features 192 vCPUs from an Intel Xeon 8559C processor, 2048.0 GB of 6 GHz DDR5 memory, and eight NVIDIA RTX Pro 6000 GPUs with 768 GB of total VRAM. The instance also bundles 15200 GB of local NVMe SSD storage and a 400 Gbps baseline network interface. In benchmark testing, the g7e.48xlarge delivers top-tier multi-core CPU performance, exceptional memory bandwidth, and rapid LLM inference speeds, including 1269.37 tokens per second for prompt processing on 70B models. This highly consolidated hardware profile provides qualitative cost efficiency for resource-intensive deployments by eliminating multi-node clustering overhead. It is designed for workloads such as large-scale LLM inference, ray tracing, high-throughput database operations, and real-time image processing.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

7.62Score
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) 27,168,987 ops/sec 1,919,696 ops/sec 14.2 50.00% 50.00% +277.00%
Redis RPS (pipeline=16, SET) 141,122,067 ops/sec 11,736,081 ops/sec 12 20.00% 20.00% +64.40%
PassMark Memory Mark (composite) 2,828 2,418 1.17 10.00% 10.00% +1.58%
Memory bandwidth (read, 16 MB ~ L3) 562,727 MB/sec 108,260 MB/sec 5.2 10.00% 10.00% +17.90%
PassMark single-thread CPU 3,147 Mops/s 2,365 Mops/s 1.33 10.00% 10.00% +2.89%

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 2,270

Geekbench Multi-Core

Score: 20,162

Passmark CPU Scores

BENCHMARKSCORE
Mark
 131267
Compression
 2884126
Encryption
 178714
Extended Instructions
 210731
Floating Point Maths
 575483
Integer Maths
 812648
Physics
 24986
Prime Numbers
 1602
Single Threaded
 3147
String Sorting
 373771

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2828
Database Operations
 37389
Memory Latency
 46
Memory Read Cached
 27623
Memory Read Uncached
 9238
Memory Write
 8894

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
g7e.2xlarge 864 GiB1
g7e.4xlarge 16128 GiB1
g7e.8xlarge 32256 GiB1
g7e.12xlarge 48512 GiB2
g7e.24xlarge 961024 GiB4

Similar Servers

INSTANCEVENDORvCPUsMEMORYGPUs

g7e.48xlarge FAQs