logo

g2-standard-32 by Google Cloud Platform

g2-standard-32 is a Graphics Optimized: 1 NVIDIA L4 GPU, 32 vCPUs, 128GB RAM server offered by Google Cloud Platform with 32 vCPUs, 128 GiB of memory and 0 GB of storage. The pricing starts at 0.4502 USD per hour.
32 vCPU
128 GiB Memory
1 GPU
Spare SCore
25296
(All-cores)
1195
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1600032
Name
g2-standard-32
Description
Graphics Optimized: 1 NVIDIA L4 GPU, 32 vCPUs, 128GB RAM
Family
g2
Hw Virt
Average Time To Start
20
Status
active
Observed At
2026-07-21T07:48:42.716316

Availability

REGION / IDSPOTONDEMAND
Ashburn (US) / us-east4
0.516 USD/h 1.1705 USD/h
Council Bluffs (US) / us-central1
0.6603 USD/h 1.1743 USD/h
The Dalles (US) / us-west1
0.6603 USD/h 1.1743 USD/h
Moncks Corner (US) / us-east1
0.6603 USD/h 1.1743 USD/h
Mumbai (IN) / asia-south1
0.5391 USD/h 1.2224 USD/h
Eemshaven (NL) / europe-west4
0.6477 USD/h 1.2343 USD/h
St. Ghislain (BE) / europe-west1
0.594 USD/h 1.2931 USD/h
Montréal (CA) / northamerica-northeast1
0.6819 USD/h 1.2931 USD/h
Toronto (CA) / northamerica-northeast2
0.6956 USD/h 1.2931 USD/h
Las Vegas (US) / us-west4
0.7683 USD/h 1.3227 USD/h
London (GB) / europe-west2
0.8022 USD/h 1.3371 USD/h
Changhua County (TW) / asia-east1
0.6428 USD/h 1.3598 USD/h
Frankfurt (DE) / europe-west3
0.8304 USD/h 1.384 USD/h
Jurong West (SG) / asia-southeast1
0.8694 USD/h 1.4488 USD/h
Seoul (KR) / asia-northeast3
0.4502 USD/h 1.5081 USD/h
Tokyo (JP) / asia-northeast1
0.9048 USD/h 1.5081 USD/h
Zurich (CH) / europe-west6
0.891 USD/h 1.5385 USD/h
Dammam (SA) / me-central2
0.9761 USD/h 1.8789 USD/h

Processor

vCPUs
32
CPU Allocation
Dedicated
CPU Cores
16
CPU Speed
2.2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU L1D Cache
32 KiB
CPU L1D Cache Total
512 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
512 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
16 MiB
CPU L3 Cache
39 MiB
CPU L3 Cache Total
39 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, 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, fsgsbase, tsc_adjust, bmi1, hle, avx2, smep, bmi2, erms, invpcid, rtm, mpx, avx512f, avx512dq, rdseed, adx, smap, clflushopt, clwb, avx512cd, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, arat, avx512_vnni, md_clear, arch_capabilities
Ecpus
21.2
Scalability
132.5

System Resources and Accelerators

MEMORY
Memory Amount
128 GiB
Memory Amount Actual
128 GiB
GPU
GPU Count
1
GPU Memory Min
22 GiB
GPU Memory Total
22 GiB
GPU Manufacturer
NVIDIA
GPU Family
Ada Lovelace
GPU Model
L4
GPUs
  • NVIDIA Ada Lovelace NVIDIA L4 (Memory amount: 23034, Firmware version: 590.48.01, BIOS version: 95.04.29.00.07, Clock rate: 2040)
STORAGE
Storage Size
0 GB
Storages
    NETWORK
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    CPU and System Topology

    Server Description

    An accelerated architecture combining dedicated Intel Xeon processors with an NVIDIA L4 GPU for efficient machine learning inference and graphics workloads.

    GPU AcceleratedGeneral Purpose

    Google Cloud Platform g2-standard-32 is a graphics-optimized server featuring 32 dedicated Intel Xeon vCPUs (16 physical cores) operating at 2.2 GHz and 128.0 GB of RAM. The hardware configuration includes a single NVIDIA L4 GPU with 22 GB of VRAM based on the Ada Lovelace architecture, while local storage is absent. Performance benchmarks indicate a clear division: single-core CPU execution and text processing are relatively weak, whereas multi-core operations and memory bandwidth perform at average levels. Most notably, the server delivers top-tier performance in LLM inference for small and medium models, processing prompts for a 7B model at 2,231.74 tokens per second. This profile makes the instance highly efficient for GPU-accelerated workloads like machine learning inference, image processing, and ray tracing, rather than general single-threaded CPU tasks.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    1.16Score
    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) 2,448,798 ops/sec 1,896,415 ops/sec 1.29 50.00% 50.00% +13.60%
    Redis RPS (pipeline=16, SET) 14,627,375 ops/sec 11,539,523 ops/sec 1.27 20.00% 20.00% +4.90%
    PassMark Memory Mark (composite) 2,588 2,411 1.07 10.00% 10.00% +0.68%
    Memory bandwidth (read, 16 MB ~ L3) 108,668 MB/sec 107,368 MB/sec 1.01 10.00% 10.00% +0.10%
    PassMark single-thread CPU 1,715 Mops/s 2,363 Mops/s 0.726 10.00% 10.00% -3.15%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,062

    Geekbench Multi-Core

    Score: 9,347

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		24012
    Compression
    		370758
    Encryption
    		11564
    Extended Instructions
    		24434
    Floating Point Maths
    		45472
    Integer Maths
    		84600
    Physics
    		2291
    Prime Numbers
    		127
    Single Threaded
    		1715
    String Sorting
    		43673

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		2588
    Database Operations
    		10267
    Memory Latency
    		52
    Memory Read Cached
    		20717
    Memory Read Uncached
    		10930
    Memory Write
    		10253

    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
    g2-standard-4 416 GiB1
    g2-standard-8 832 GiB1
    g2-standard-12 1248 GiB1
    g2-standard-16 1664 GiB1
    g2-standard-24 2496 GiB2
    g2-standard-48 48192 GiB4
    g2-standard-96 96384 GiB8

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYGPUs

    g2-standard-32 FAQs