c8gd.12xlarge by Amazon Web Services

c8gd.12xlarge is a Compute optimized [AWS Graviton processors] [Instance store volumes] Gen8 12xlarge server offered by Amazon Web Services with 48 vCPUs, 96 GiB of memory and 2.85 TB of storage. The pricing starts at 0.2547 USD per hour.
48 vCPU
96 GiB Memory
2.85 TB Storage
Spare SCore
81,874
(All-cores)
1,707
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
c8gd.12xlarge
Description
Compute optimized [AWS Graviton processors] [Instance store volumes] Gen8 12xlarge
Family
c8gd
Hw Virt
Status
active
Observed At
2026-11-05T11:15:13.518868

Availability

REGION / IDSPOTONDEMAND
Mumbai (IN) / ap-south-1
0.36045 USD/h 1.4928 USD/h
(MY) / ap-southeast-5
0.734033 USD/h 2.3318 USD/h
(TH) / ap-southeast-7
0.901933 USD/h 2.3318 USD/h
Ohio (US) / us-east-2
0.508533 USD/h 2.3515 USD/h
Northern Virgina (US) / us-east-1
0.71098 USD/h 2.3515 USD/h
Oregon (US) / us-west-2
0.8535 USD/h 2.3515 USD/h
Stockholm (SE) / eu-north-1
0.2815 USD/h 2.5474 USD/h
Quebec (CA) / ca-central-1
0.418433 USD/h 2.5963 USD/h
Aragón (ES) / eu-south-2
1.035067 USD/h 2.6698 USD/h
Dublin (IE) / eu-west-1
0.958067 USD/h 2.6698 USD/h
Seoul (KR) / ap-northeast-2
0.634 USD/h 2.6947 USD/h
Frankfurt (DE) / eu-central-1
0.9122 USD/h 2.7192 USD/h
Singapore (SG) / ap-southeast-1
0.5997 USD/h 2.7432 USD/h
London (GB) / eu-west-2
0.553367 USD/h 2.8166 USD/h
Tokyo (JP) / ap-northeast-1
0.677967 USD/h 2.9885 USD/h
Sydney (AU) / ap-southeast-2
0.7735 USD/h 3.0864 USD/h
(NZ) / ap-southeast-6
1.2001 USD/h 3.241 USD/h
Sao Paulo (BR) / sa-east-1
1.5597 USD/h 3.6494 USD/h

Processor

vCPUs
48
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
48
CPU Speed
2.8 GHz
CPU Architecture
arm64
CPU Manufacturer
AWS
CPU Family
ARMv9
CPU Model
Neoverse-V2
CPU L1D Cache
64 KiB
CPU L1D Cache Total
3 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
3 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
96 MiB
CPU L3 Cache
36 MiB
CPU L3 Cache Total
36 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
48
Scalability
100

System Resources and Accelerators

MEMORY
Memory Amount
96 GiB
Memory Amount Actual
95 GiB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    2850 GB
    Storage Type
    nvme ssd
    Storages
    • 950 GB nvme ssd
    • 950 GB nvme ssd
    • 950 GB nvme ssd
    NETWORK
    Network Speed Baseline
    22.5 Gbps
    Network Speed Max
    22.5 Gbps
    Network Storage Speed Baseline
    15 Gbps
    Network Storage Speed Max
    15 Gbps
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    Server Description

    An ARM-based compute instance with dedicated physical cores and high-speed local NVMe SSD storage designed for scalable parallel processing.

    Compute OptimizedStorage & Database

    Amazon Web Services c8gd.12xlarge is a compute-optimized ARM64 server powered by 48 dedicated physical cores of AWS ARMv9 Neoverse-V2 running at 2.8 GHz. Managed by the AWS Nitro hypervisor, the instance includes 96 GB of RAM (2 GB per core), 22 Gbps of baseline network bandwidth, and a bundled 2850 GB local NVMe SSD. Benchmark data highlights top-tier multi-core performance and memory bandwidth, achieving 381.77 GB/sec uncached memory reads and high software compilation speeds. It demonstrates strong throughput in static web serving and Redis caching. Tradeoffs include an average single-core performance profile, a relatively low memory-to-core ratio, and the absence of discrete GPU hardware or x86 instruction sets. This instance delivers effective cost efficiency for parallelized build environments, web serving, and database workloads requiring low-latency local storage.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    3.8Score
    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) 11,025,511 ops/sec 1,937,246 ops/sec 5.8 50.00% 50.00% +140.00%
    Redis RPS (pipeline=16, SET) 59,296,576 ops/sec 11,803,344 ops/sec 4.9 20.00% 20.00% +37.00%
    PassMark Memory Mark (composite) 3,204 2,409 1.3 10.00% 10.00% +2.70%
    Memory bandwidth (read, 16 MB ~ L3) 434,456 MB/sec 108,490 MB/sec 3.9 10.00% 10.00% +15.00%
    PassMark single-thread CPU 1,941 Mops/s 2,365 Mops/s 0.79 10.00% 10.00% -2.30%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,826

    Geekbench Multi-Core

    Score: 23,361

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 35,961
    Compression
    		 319,121
    Encryption
    		 9,067
    Extended Instructions
    		 43,769
    Floating Point Maths
    		 290,967
    Integer Maths
    		 250,387
    Physics
    		 11,869
    Prime Numbers
    		 507
    Single Threaded
    		 1,941
    String Sorting
    		 219,287

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 3,204
    Database Operations
    		 46,215
    Memory Latency
    		 51
    Memory Read Cached
    		 21,127
    Memory Read Uncached
    		 19,181
    Memory Write
    		 21,174

    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.16xlarge 64128 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    c8gd.12xlarge FAQs