m9gd.48xlarge by Amazon Web Services

m9gd.48xlarge is a General purpose [AWS Graviton processors] [Instance store volumes] Gen9 48xlarge server offered by Amazon Web Services with 192 vCPUs, 768 GiB of memory and 11.4 TB of storage. The pricing starts at 1.4629 USD per hour.
192 vCPU
768 GiB Memory
11.4 TB Storage
Spare SCore
382,376
(All-cores)
2,009
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
m9gd.48xlarge
Description
General purpose [AWS Graviton processors] [Instance store volumes] Gen9 48xlarge
Family
m9gd
Hw Virt
Average Time To Start
20
Status
active
Observed At
2026-10-24T11:37:54.199043

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
1.960067 USD/h 12.0672 USD/h
Northern Virgina (US) / us-east-1
3.023625 USD/h 12.0672 USD/h
Oregon (US) / us-west-2
3.92785 USD/h 12.0672 USD/h
(MY) / ap-southeast-5
4.129133 USD/h 12.7987 USD/h
Aragón (ES) / eu-south-2
2.8853 USD/h 13.4573 USD/h
Dublin (IE) / eu-west-1
6.817433 USD/h 13.4573 USD/h
Frankfurt (DE) / eu-central-1
4.312933 USD/h 14.5248 USD/h
Singapore (SG) / ap-southeast-1
4.6215 USD/h 15.0586 USD/h
Sydney (AU) / ap-southeast-2
2.878133 USD/h 15.1642 USD/h
Tokyo (JP) / ap-northeast-1
2.9357 USD/h 15.5904 USD/h

Processor

vCPUs
192
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
192
CPU Speed
3.3 GHz
CPU Architecture
arm64
CPU Manufacturer
AWS
CPU Family
ARMv9
CPU Model
Neoverse-V3
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
96 MiB
CPU L3 Cache Total
192 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, sb, paca, pacg, dcpodp, sve2, sveaes, svepmull, svebitperm, svesha3, flagm2, frint, svei8mm, svebf16, i8mm, bf16, dgh, rng, bti, ecv, afp, wfxt
Ecpus
190.3
Scalability
99.11

System Resources and Accelerators

MEMORY
Memory Amount
768 GiB
Memory Amount Actual
756 GiB
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
    • 3800 GB nvme ssd
    • 3800 GB nvme ssd
    • 3800 GB nvme ssd
    NETWORK
    Network Speed Baseline
    100 Gbps
    Network Speed Max
    100 Gbps
    Network Storage Speed Baseline
    72 Gbps
    Network Storage Speed Max
    72 Gbps
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    CPU and System Topology

    Server Description

    A high-density ARMv9 instance featuring massive local NVMe storage and top-tier multi-core performance for demanding database and web serving workloads.

    General PurposeStorage & DatabaseCompute Optimized

    Amazon Web Services m9gd.48xlarge is a general-purpose instance powered by 192 dedicated AWS Graviton ARMv9 Neoverse-V3 physical cores running at 3.3 GHz. It features 768 GB of RAM, 11,400 GB of local NVMe SSD storage, and 100 Gbps of baseline network bandwidth. Operating on the Nitro hypervisor, this instance delivers top-tier multi-core CPU and memory bandwidth performance, ranking in the top 10% for multi-threaded benchmarks. It excels in database operations, achieving 506.95 million Redis SET operations per second and top-tier static web serving throughput. While single-core performance is moderate, the high core density and integrated local storage offer excellent resource efficiency for concurrent workloads. The m9gd.48xlarge is highly suited for large-scale databases, multi-threaded data processing, and high-throughput web serving, though it is not optimized for GPU-accelerated tasks.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    15Score
    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) 61,687,951 ops/sec 1,919,289 ops/sec 33 50.00% 50.00% +470.00%
    Redis RPS (pipeline=16, SET) 372,038,882 ops/sec 11,728,058 ops/sec 31 20.00% 20.00% +99.00%
    PassMark Memory Mark (composite) 4,636 2,416 1.9 10.00% 10.00% +6.60%
    Memory bandwidth (read, 16 MB ~ L3) 844,607 MB/sec 108,466 MB/sec 7.6 10.00% 10.00% +22.00%
    PassMark single-thread CPU 2,465 Mops/s 2,365 Mops/s 1 10.00% 10.00% 0.00%

    Memory Bandwidth

    Compression

    OpenSSL

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 107,020
    Compression
    		 1,759,110
    Encryption
    		 55,789
    Extended Instructions
    		 243,528
    Floating Point Maths
    		 1,456,384
    Integer Maths
    		 1,168,147
    Physics
    		 41,773
    Prime Numbers
    		 2,201
    Single Threaded
    		 2,465
    String Sorting
    		 897,788

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 4,636
    Database Operations
    		 61,965
    Memory Latency
    		 29
    Memory Read Cached
    		 24,755
    Memory Read Uncached
    		 24,495
    Memory Write
    		 25,023

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 150.64 - -
    bitops
    		 162,005 11,842,272 73.10×
    branch
    		 320,378 28,032,327 87.50×
    funccall
    		 2,284 433,650 189.87×
    funcret
    		 39,748 7,213,574 181.48×
    hash
    		 181,482 34,280,486 188.89×
    intmath
    		 39,545 7,471,864 188.95×
    nop
    		 430,062 81,808,945 190.23×
    prime
    		 600,283 112,440,290 187.31×
    rotate
    		 149,250 28,308,444 189.67×
    str
    		 934,193 176,954,900 189.42×
    wcs
    		 282,857 52,914,957 187.07×
    CryptographySingleMultiScaling
    crypt
    		 4,297 827,905 192.67×
    CompressionSingleMultiScaling
    jpeg
    		 917.15 109,487 119.38×
    zlib
    		 60.65 9,026 148.82×
    HypervisorSingleMultiScaling
    clock
    		 39,792 138,834 3.49×
    clone
    		 331.8 21,010 63.32×
    context
    		 3,956 755,625 191.01×
    cpu-sched
    		 77.74 11,915 153.26×
    eventfd
    		 130,429 4,313,680 33.07×
    fault
    		 27,954 279,362 9.99×
    fork
    		 5,149 67,882 13.18×
    getrandom
    		 74,086 14,038,172 189.48×
    hrtimers
    		 642,881 8,771,354 13.64×
    mprotect
    		 922,933 18,565,442 20.12×
    mtx
    		 13,244,923 10,334,190,577 780.24×
    munmap
    		 3,857 90,585 23.48×
    null
    		 681,011 131,407,694 192.96×
    pipe
    		 1,049,277 85,341,268 81.33×
    priv-instr
    		 1,092,620 9,026,002 8.26×
    resched
    		 1,147,311 29,659,188 25.85×
    switch
    		 272,391 113,731,086 417.53×
    timermix
    		 600,122 34,547,026 57.57×
    tlb-shootdown
    		 15,192 201,690 13.28×
    vdso
    		 64,319,772 11,642,815,870 181.01×
    vfork
    		 40,150 268,363 6.68×
    yield
    		 353,848,548 360,748,909 1.02×
    zero
    		 3,265,215 621,474,349 190.33×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 2,246 423,966 188.77×
    expmath
    		 425.43 79,182 186.12×
    fma
    		 853,457 162,120,114 189.96×
    fp
    		 175.2 33,102 188.94×
    fractal
    		 9.2 1,709 185.72×
    hyperbolic
    		 408.58 77,756 190.31×
    logmath
    		 491.58 93,501 190.20×
    matrix
    		 7,996 1,515,244 189.50×
    matrix-3d
    		 1,511 34,296 22.69×
    monte-carlo
    		 269.53 51,029 189.33×
    mpfr
    		 1,890 357,426 189.16×
    powmath
    		 282.22 53,624 190.01×
    trig
    		 554.06 105,000 189.51×
    veccmp
    		 26,363 4,986,258 189.14×
    vecfp
    		 1,861 351,713 188.96×
    vecmath
    		 4,817 908,710 188.63×
    vecshuf
    		 1,027 195,958 190.78×
    vecwide
    		 30,078 5,722,296 190.25×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 11.2 764.28 68.24×
    bsearch
    		 422.78 79,947 189.10×
    bubblesort
    		 1.4 268.4 191.71×
    fibsearch
    		 414.72 78,900 190.25×
    heapsort
    		 15.4 2,889 187.59×
    hsearch
    		 10,810 2,002,428 185.23×
    insertionsort
    		 7.6 1,422 187.05×
    malloc
    		 4,160,005 305,111,432 73.34×
    mcontend
    		 161.92 493,128 3045.50×
    mergesort
    		 38.6 7,070 183.15×
    qsort
    		 26.6 5,011 188.40×
    skiplist
    		 7,671 1,459,599 190.28×
    tree
    		 1.8 190.75 105.97×
    MemorySingleMultiScaling
    cache
    		 590,933 7,591,778 12.85×
    cachehammer
    		 2,139,726 18,635,116 8.71×
    cacheline
    		 56.37 4,093 72.61×
    l1cache
    		 389.23 59,332 152.44×
    memcpy
    		 1,018 173,665 170.59×
    memrate
    		 6.71 95.61 14.25×
    memthrash
    		 534.66 356.63 0.67×
    ptr-chase
    		 29,088,062 1,718,045,629 59.06×
    spinmem
    		 3,012 179,675 59.65×
    stream
    		 26.21 232,233 8860.48×
    vm
    		 198,289 5,140,991 25.93×

    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
    m9gd.medium 14 GiB0
    m9gd.large 28 GiB0
    m9gd.xlarge 416 GiB0
    m9gd.2xlarge 832 GiB0
    m9gd.4xlarge 1664 GiB0
    m9gd.8xlarge 32128 GiB0
    m9gd.12xlarge 48192 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    m9gd.48xlarge FAQs