g2-standard-24 by Google Cloud Platform

g2-standard-24 is a Graphics Optimized: 2 NVIDIA L4 GPUs, 24 vCPUs, 96GB RAM server offered by Google Cloud Platform with 24 vCPUs, 96 GiB of memory and 0 GB of storage. The pricing starts at 0.3676 USD per hour.
24 vCPU
96 GiB Memory
2 GPU
Spare SCore
18,985
(All-cores)
1,201
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1600024
Name
g2-standard-24
Description
Graphics Optimized: 2 NVIDIA L4 GPUs, 24 vCPUs, 96GB RAM
Family
g2
Hw Virt
Average Time To Start
20
Status
active
Observed At
2026-09-12T09:38:50.014421

Availability

REGION / IDSPOTONDEMAND
Ashburn (US) / us-east4
0.4258 USD/h 0.8779 USD/h
Council Bluffs (US) / us-central1
0.5019 USD/h 0.8808 USD/h
The Dalles (US) / us-west1
0.5019 USD/h 0.8808 USD/h
Moncks Corner (US) / us-east1
0.5019 USD/h 0.8808 USD/h
Mumbai (IN) / asia-south1
0.4448 USD/h 0.9168 USD/h
Eemshaven (NL) / europe-west4
0.5277 USD/h 0.9257 USD/h
St. Ghislain (BE) / europe-west1
0.5118 USD/h 0.9698 USD/h
Toronto (CA) / northamerica-northeast2
0.5513 USD/h 0.9698 USD/h
Montréal (CA) / northamerica-northeast1
0.5527 USD/h 0.9698 USD/h
Las Vegas (US) / us-west4
0.5653 USD/h 0.992 USD/h
London (GB) / europe-west2
0.6017 USD/h 1.0028 USD/h
Changhua County (TW) / asia-east1
0.554 USD/h 1.0198 USD/h
Frankfurt (DE) / europe-west3
0.5903 USD/h 1.038 USD/h
Jurong West (SG) / asia-southeast1
0.652 USD/h 1.0866 USD/h
Seoul (KR) / asia-northeast3
0.3676 USD/h 1.1311 USD/h
Tokyo (JP) / asia-northeast1
0.6447 USD/h 1.1311 USD/h
Zurich (CH) / europe-west6
0.6577 USD/h 1.1538 USD/h
Dammam (SA) / me-central2
0.8012 USD/h 1.4092 USD/h

Processor

vCPUs
24
CPU Allocation
Dedicated
CPU Cores
12
CPU Speed
2.2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU L1D Cache
32 KiB
CPU L1D Cache Total
384 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
384 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
12 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
15.8
Scalability
131.67

System Resources and Accelerators

MEMORY
Memory Amount
96 GiB
Memory Amount Actual
96 GiB
GPU
GPU Count
2
GPU Memory Min
22 GiB
GPU Memory Total
45 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)
  • 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

    A dual-GPU accelerated virtual machine delivering top-tier LLM inference performance balanced with moderate multi-core x86_64 compute resources.

    GPU AcceleratedGeneral Purpose

    Google Cloud Platform g2-standard-24 is a graphics-optimized virtual machine configured with 24 vCPUs, 96 GB of RAM, and two NVIDIA L4 GPUs providing 45 GB of VRAM. Powered by an Intel Xeon x86_64 processor with 12 physical cores running at 2.2 GHz, this instance does not include local storage. Performance benchmarks reveal a distinct tradeoff: single-core CPU performance is weak, but GPU-accelerated capabilities are exceptional. The instance achieves top-tier results in LLM inference, processing up to 11,848 tokens per second for small models and maintaining strong text generation speeds. Multi-core CPU tasks and memory bandwidth perform at average levels. Qualitatively, this server provides a cost-effective entry point for GPU-intensive applications by balancing moderate CPU capabilities with dual Ada Lovelace accelerators. It is best suited for LLM inference, machine learning deployment, ray tracing, and image processing workloads.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    0.961Score
    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) 1,877,652 ops/sec 1,917,397 ops/sec 0.979 50.00% 50.00% -1.06%
    Redis RPS (pipeline=16, SET) 11,452,540 ops/sec 11,681,410 ops/sec 0.98 20.00% 20.00% -0.40%
    PassMark Memory Mark (composite) 2,543 2,418 1.05 10.00% 10.00% +0.49%
    Memory bandwidth (read, 16 MB ~ L3) 110,082 MB/sec 108,140 MB/sec 1.02 10.00% 10.00% +0.20%
    PassMark single-thread CPU 1,713 Mops/s 2,365 Mops/s 0.724 10.00% 10.00% -3.18%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,059

    Geekbench Multi-Core

    Score: 8,145

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 19045
    Compression
    		 278913
    Encryption
    		 8663
    Extended Instructions
    		 18063
    Floating Point Maths
    		 34111
    Integer Maths
    		 63470
    Physics
    		 1945
    Prime Numbers
    		 102
    Single Threaded
    		 1713
    String Sorting
    		 32680

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2543
    Database Operations
    		 7776
    Memory Latency
    		 52
    Memory Read Cached
    		 20669
    Memory Read Uncached
    		 10575
    Memory Write
    		 9969

    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-32 32128 GiB1
    g2-standard-48 48192 GiB4
    g2-standard-96 96384 GiB8

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYGPUs

    g2-standard-24 FAQs