z3-highmem-16-highlssd by Google Cloud Platform

z3-highmem-16-highlssd is a 16 vCPUs, 128 GB RAM, 2 Local SSDs server offered by Google Cloud Platform with 16 vCPUs, 128 GiB of memory and 6.44 TB of storage. The pricing starts at 0.2573 USD per hour.
16 vCPU
128 GiB Memory
6.44 TB Storage
Spare SCore
13,297
(All-cores)
1,622
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1742009
Name
z3-highmem-16-highlssd
Description
16 vCPUs, 128 GB RAM, 2 Local SSDs
Family
z3
Hw Virt
Average Time To Start
26
Status
active
Observed At
2026-11-01T17:36:59.048102

Availability

REGION / IDSPOTONDEMAND
Ashburn (US) / us-east4
0.2845 USD/h 2.3039 USD/h
Council Bluffs (US) / us-central1
1.3014 USD/h 2.3039 USD/h
The Dalles (US) / us-west1
1.3014 USD/h 2.3039 USD/h
Moncks Corner (US) / us-east1
1.3014 USD/h 2.3039 USD/h
Mumbai (IN) / asia-south1
0.2573 USD/h 2.396 USD/h
Eemshaven (NL) / europe-west4
0.3606 USD/h 2.4191 USD/h
Stockholm (SE) / europe-north2
0.8701 USD/h 2.4191 USD/h
Queretaro (MX) / northamerica-south1
0.9032 USD/h 2.5112 USD/h
Columbus (US) / us-east5
0.8954 USD/h 2.5973 USD/h
London (GB) / europe-west2
0.6907 USD/h 2.6264 USD/h
Dallas (US) / us-south1
0.4471 USD/h 2.7186 USD/h
Frankfurt (DE) / europe-west3
0.4909 USD/h 2.7186 USD/h
Jurong West (SG) / asia-southeast1
0.4428 USD/h 2.8398 USD/h
Sydney (AU) / australia-southeast1
0.3897 USD/h 2.8798 USD/h
Berlin (DE) / europe-west10
0.2641 USD/h 2.9326 USD/h
Tokyo (JP) / asia-northeast1
0.7367 USD/h 2.9559 USD/h
St. Ghislain (BE) / europe-west1
0.603 USD/h 3.0181 USD/h
Zurich (CH) / europe-west6
0.2994 USD/h 3.0198 USD/h

Processor

vCPUs
16
CPU Allocation
Dedicated
CPU Cores
8
CPU Speed
2.7 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
8481C
CPU L1D Cache
48 KiB
CPU L1D Cache Total
384 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
256 KiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
16 MiB
CPU L3 Cache
105 MiB
CPU L3 Cache Total
105 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, rep_good, nopl, xtopology, nonstop_tsc, cpuid, tsc_known_freq, pni, pclmulqdq, vmx, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, ssbd, ibrs, ibpb, stibp, ibrs_enhanced, tpr_shadow, flexpriority, ept, vpid, ept_ad, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, erms, invpcid, rtm, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, avx_vnni, avx512_bf16, arat, vnmi, avx512vbmi, umip, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, la57, rdpid, cldemote, movdiri, movdir64b, fsrm, md_clear, serialize, tsxldtrk, amx_bf16, avx512_fp16, amx_tile, amx_int8, arch_capabilities
Ecpus
8.2
Scalability
51.25

System Resources and Accelerators

MEMORY
Memory Amount
128 GiB
Memory Amount Actual
128 GiB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    6442 GB
    Storage Type
    nvme ssd
    Storages
    • 3221 GB nvme ssd
    • 3221 GB nvme ssd
    NETWORK
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    CPU and System Topology

    Server Description

    A memory-optimized server featuring dedicated Intel Xeon processors and massive bundled NVMe storage for high-throughput database and caching workloads.

    Memory OptimizedStorage & Database

    Google Cloud Platform z3-highmem-16-highlssd is a memory-optimized server designed for data-intensive workloads. It features 16 dedicated vCPUs powered by an Intel Xeon 8481C processor running at 2.7 GHz, paired with 128 GB of RAM and a substantial 6442 GB of local NVMe SSD storage. The server lacks GPU acceleration but leverages advanced CPU instructions, including Intel AMX and AVX-512. Benchmarks show balanced performance, with a Passmark CPU score of 21549.51 and a strong LLM text generation speed of 264.49 tokens/sec for small models. With a high memory-to-vCPU ratio of 8 GB per core and massive bundled storage, this server is highly cost-efficient for memory-heavy databases, caching systems, and local data processing tasks.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    1.1Score
    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) 2,359,588 ops/sec 1,918,343 ops/sec 1.3 50.00% 50.00% +14.00%
    Redis RPS (pipeline=16, SET) 12,144,677 ops/sec 11,704,734 ops/sec 1 20.00% 20.00% 0.00%
    PassMark Memory Mark (composite) 2,124 2,416 0.88 10.00% 10.00% -1.30%
    Memory bandwidth (read, 16 MB ~ L3) 100,012 MB/sec 108,466 MB/sec 0.91 10.00% 10.00% -0.94%
    PassMark single-thread CPU 2,420 Mops/s 2,365 Mops/s 1 10.00% 10.00% 0.00%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,691

    Geekbench Multi-Core

    Score: 10,293

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 21,550
    Compression
    		 228,453
    Encryption
    		 14,100
    Extended Instructions
    		 15,575
    Floating Point Maths
    		 45,343
    Integer Maths
    		 63,584
    Physics
    		 2,603
    Prime Numbers
    		 135
    Single Threaded
    		 2,420
    String Sorting
    		 31,551

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2,124
    Database Operations
    		 7,661
    Memory Latency
    		 73
    Memory Read Cached
    		 22,341
    Memory Read Uncached
    		 9,264
    Memory Write
    		 8,288

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 202 161.76 0.80×
    bitops
    		 124,630 1,202,239 9.65×
    branch
    		 115,984 1,443,265 12.44×
    funccall
    		 625.13 6,518 10.43×
    funcret
    		 10,442 132,004 12.64×
    hash
    		 148,454 1,737,816 11.71×
    intmath
    		 54,073 517,257 9.57×
    nop
    		 221,682 1,459,621 6.58×
    prime
    		 396,777 3,757,587 9.47×
    rotate
    		 83,531 721,970 8.64×
    str
    		 786,877 9,029,225 11.47×
    wcs
    		 571,889 5,832,748 10.20×
    CryptographySingleMultiScaling
    crypt
    		 2,824 21,753 7.70×
    CompressionSingleMultiScaling
    jpeg
    		 680.74 7,175 10.54×
    zlib
    		 47.59 614.63 12.92×
    HypervisorSingleMultiScaling
    clock
    		 43,674 318,554 7.29×
    clone
    		 488.72 2,679 5.48×
    context
    		 4,380 58,060 13.26×
    cpu-sched
    		 63.32 1,022 16.15×
    eventfd
    		 57,517 636,599 11.07×
    fault
    		 25,243 194,200 7.69×
    fork
    		 5,790 51,215 8.85×
    getrandom
    		 49,570 579,531 11.69×
    hrtimers
    		 734,905 2,234,348 3.04×
    mprotect
    		 1,136,255 4,491,251 3.95×
    mtx
    		 10,809,642 479,892,998 44.39×
    munmap
    		 4,316 42,401 9.82×
    null
    		 749,699 9,366,425 12.49×
    pipe
    		 715,156 12,359,655 17.28×
    priv-instr
    		 699,645 7,513,125 10.74×
    resched
    		 6,541,429 1,068,047 0.16×
    switch
    		 77,236 4,168,873 53.98×
    timermix
    		 203,344 2,639,488 12.98×
    tlb-shootdown
    		 7,965 31,515 3.96×
    tsc
    		 487,563 6,400,204 13.13×
    usersyscall
    		 594,136 6,586,774 11.09×
    vdso
    		 71,272,000 871,318,770 12.23×
    vfork
    		 36,699 244,413 6.66×
    x86syscall
    		 8,378,482 112,428,380 13.42×
    yield
    		 13,641,150 14,330,373 1.05×
    zero
    		 5,412,304 68,250,718 12.61×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 12,928 138,803 10.74×
    expmath
    		 2,928 34,397 11.75×
    fma
    		 1,161,695 13,042,643 11.23×
    fp
    		 258.39 3,203 12.40×
    fractal
    		 5.8 67.6 11.66×
    hyperbolic
    		 3,388 39,318 11.61×
    logmath
    		 4,372 55,186 12.62×
    matrix
    		 5,190 46,440 8.95×
    matrix-3d
    		 663.97 2,957 4.45×
    monte-carlo
    		 246.92 3,171 12.84×
    mpfr
    		 1,452 13,014 8.96×
    powmath
    		 1,623 19,849 12.23×
    trig
    		 2,208 23,565 10.67×
    veccmp
    		 20,585 192,763 9.36×
    vecfp
    		 1,838 17,074 9.29×
    vecmath
    		 3,230 37,353 11.57×
    vecshuf
    		 3,219 48,336 15.01×
    vecwide
    		 63,479 653,488 10.29×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 7.4 70.6 9.54×
    bsearch
    		 241.33 2,432 10.08×
    bubblesort
    		 0.8 9.6 12.00×
    fibsearch
    		 262.9 2,546 9.68×
    heapsort
    		 8.4 89.6 10.67×
    hsearch
    		 7,031 68,222 9.70×
    insertionsort
    		 10.6 76.2 7.19×
    malloc
    		 2,502,798 26,277,997 10.50×
    mcontend
    		 106.49 2,546 23.91×
    mergesort
    		 25.8 296.99 11.51×
    qsort
    		 18.4 204.99 11.14×
    skiplist
    		 4,578 57,891 12.64×
    tree
    		 1.4 12.79 9.14×
    MemorySingleMultiScaling
    cache
    		 270,157 635,207 2.35×
    cachehammer
    		 201,184 2,526,966 12.56×
    cacheline
    		 58.72 913.9 15.56×
    l1cache
    		 910.69 2,849 3.13×
    memcpy
    		 373.02 2,863 7.67×
    memrate
    		 0.12 1.8 15.00×
    memthrash
    		 193.04 513.74 2.66×
    ptr-chase
    		 28,731,423 148,162,127 5.16×
    spinmem
    		 219.99 744 3.38×
    stream
    		 14.45 1,312 90.77×
    vm
    		 96,416 293,503 3.04×

    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
    z3-highmem-8-highlssd 864 GiB0
    z3-highmem-14-standardlssd 14112 GiB0
    z3-highmem-22-highlssd 22176 GiB0
    z3-highmem-22-standardlssd 22176 GiB0
    z3-highmem-32-highlssd 32256 GiB0
    z3-highmem-44-highlssd 44352 GiB0
    z3-highmem-44-standardlssd 44352 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    z3-highmem-16-highlssd FAQs