c8gd.metal-48xl by Amazon Web Services

c8gd.metal-48xl is a Compute optimized [AWS Graviton processors] [Instance store volumes] Gen8 metal-48xl server offered by Amazon Web Services with 192 vCPUs, 384 GiB of memory and 11.4 TB of storage. The pricing starts at 0.9327 USD per hour.
192 vCPU
384 GiB Memory
11.4 TB Storage
Spare SCore
301,158
(All-cores)
1,649
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
c8gd.metal-48xl
Description
Compute optimized [AWS Graviton processors] [Instance store volumes] Gen8 metal-48xl
Family
c8gd
Hw Virt
Status
active
Observed At
2026-11-05T15:02:00.217078

Availability

REGION / IDSPOTONDEMAND
Mumbai (IN) / ap-south-1
1.1697 USD/h 5.9712 USD/h
(TH) / ap-southeast-7
2.981533 USD/h 9.3274 USD/h
(MY) / ap-southeast-5
1.385967 USD/h 9.3274 USD/h
Ohio (US) / us-east-2
1.725933 USD/h 9.4061 USD/h
Northern Virgina (US) / us-east-1
1.81532 USD/h 9.4061 USD/h
Oregon (US) / us-west-2
2.419 USD/h 9.4061 USD/h
Stockholm (SE) / eu-north-1
3.4837 USD/h 10.1894 USD/h
Quebec (CA) / ca-central-1
1.5197 USD/h 10.3853 USD/h
Aragón (ES) / eu-south-2
4.189567 USD/h 10.679 USD/h
Dublin (IE) / eu-west-1
4.0083 USD/h 10.679 USD/h
Seoul (KR) / ap-northeast-2
1.2898 USD/h 10.7789 USD/h
Frankfurt (DE) / eu-central-1
1.408067 USD/h 10.8768 USD/h
Singapore (SG) / ap-southeast-1
1.1445 USD/h 10.9728 USD/h
London (GB) / eu-west-2
1.208033 USD/h 11.2666 USD/h
Tokyo (JP) / ap-northeast-1
1.977167 USD/h 11.9539 USD/h
Sydney (AU) / ap-southeast-2
1.2346 USD/h 12.3456 USD/h
(NZ) / ap-southeast-6
1.2964 USD/h 12.9638 USD/h
Sao Paulo (BR) / sa-east-1
1.4598 USD/h 14.5978 USD/h

Processor

vCPUs
192
CPU Allocation
Dedicated
CPU Cores
192
CPU Speed
2.7 GHz
CPU Architecture
arm64
CPU Manufacturer
AWS
CPU Family
ARMv9
CPU Model
Neoverse-V2
CPU L1D Cache
64 KiB
CPU L1D Cache Total
12 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
12 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
384 MiB
CPU L3 Cache
36 MiB
CPU L3 Cache Total
72 MiB
CPU Flags
fp, asimd, evtstrm, aes, pmull, sha1, sha2, crc32, atomics, fphp, asimdhp, cpuid, asimdrdm, jscvt, fcma, lrcpc, dcpop, sha3, asimddp, sha512, sve, asimdfhm, dit, uscat, ilrcpc, flagm, ssbs, sb, paca, pacg, dcpodp, sve2, sveaes, svepmull, svebitperm, svesha3, flagm2, frint, svei8mm, svebf16, i8mm, bf16, dgh, rng, bti
Ecpus
182.7
Scalability
95.16

System Resources and Accelerators

MEMORY
Memory Amount
384 GiB
Memory Amount Actual
384 GiB
Memory Generation
DDR5
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    11400 GB
    Storage Type
    nvme ssd
    Storages
    • 1900 GB nvme ssd
    • 1900 GB nvme ssd
    • 1900 GB nvme ssd
    • 1900 GB nvme ssd
    • 1900 GB nvme ssd
    • 1900 GB nvme ssd
    NETWORK
    Network Speed Baseline
    50 Gbps
    Network Speed Max
    50 Gbps
    Network Storage Speed Baseline
    40 Gbps
    Network Storage Speed Max
    40 Gbps
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    Server Description

    A 192-core bare-metal Arm instance featuring 11.4 TB local NVMe storage, delivering top-tier multi-core compute throughput and high memory bandwidth.

    Compute OptimizedStorage & Database

    Amazon Web Services c8gd.metal-48xl is a compute-optimized bare-metal instance powered by 192 physical ARMv9 Neoverse-V2 cores running at 2.7 GHz. Equipped with 384 GB of DDR5 RAM (2 GB per core) and 11,400 GB of direct-attached local NVMe SSD storage, it offers a 50 Gbps baseline network capacity. In benchmarks, the server demonstrates top-tier multi-core performance, memory bandwidth, and software compilation speed, along with top-tier throughput in Redis SET operations and database tasks. However, single-threaded performance is in the average tier, and LLM text generation speeds are low. This instance provides scalable processing density for multi-threaded workloads, fitting high-throughput databases, software compilation, static web serving, and parallel data processing.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    9.5Score
    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) 34,658,801 ops/sec 1,933,252 ops/sec 18 50.00% 50.00% +320.00%
    Redis RPS (pipeline=16, SET) 217,441,162 ops/sec 11,794,699 ops/sec 18 20.00% 20.00% +78.00%
    PassMark Memory Mark (composite) 3,317 2,408 1.4 10.00% 10.00% +3.40%
    Memory bandwidth (read, 16 MB ~ L3) 955,331 MB/sec 108,490 MB/sec 8.7 10.00% 10.00% +24.00%
    PassMark single-thread CPU 1,873 Mops/s 2,365 Mops/s 0.79 10.00% 10.00% -2.30%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,670

    Geekbench Multi-Core

    Score: 20,349

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 77,384
    Compression
    		 1,219,802
    Encryption
    		 34,399
    Extended Instructions
    		 140,379
    Floating Point Maths
    		 1,120,661
    Integer Maths
    		 964,602
    Physics
    		 35,082
    Prime Numbers
    		 1,521
    Single Threaded
    		 1,873
    String Sorting
    		 831,592

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 3,317
    Database Operations
    		 45,539
    Memory Latency
    		 47
    Memory Read Cached
    		 20,291
    Memory Read Uncached
    		 18,669
    Memory Write
    		 20,505

    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
    c8gd.medium 12 GiB0
    c8gd.large 24 GiB0
    c8gd.xlarge 48 GiB0
    c8gd.2xlarge 816 GiB0
    c8gd.4xlarge 1632 GiB0
    c8gd.8xlarge 3264 GiB0
    c8gd.12xlarge 4896 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    c8gd.metal-48xl FAQs