g2-standard-4 by Google Cloud Platform

g2-standard-4 is a Graphics Optimized: 1 NVIDIA L4 GPU, 4 vCPUs, 16GB RAM server offered by Google Cloud Platform with 4 vCPUs, 16 GiB of memory and 0 GB of storage. The pricing starts at 0.0613 USD per hour.
4 vCPU
16 GiB Memory
1 GPU
Spare SCore
3,149
(All-cores)
1,198
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1600004
Name
g2-standard-4
Description
Graphics Optimized: 1 NVIDIA L4 GPU, 4 vCPUs, 16GB RAM
Family
g2
Hw Virt
Average Time To Start
22
Status
active
Observed At
2026-09-11T04:47:38.130842

Availability

REGION / IDSPOTONDEMAND
Ashburn (US) / us-east4
0.071 USD/h 0.1463 USD/h
Council Bluffs (US) / us-central1
0.0836 USD/h 0.1468 USD/h
The Dalles (US) / us-west1
0.0836 USD/h 0.1468 USD/h
Moncks Corner (US) / us-east1
0.0836 USD/h 0.1468 USD/h
Mumbai (IN) / asia-south1
0.0741 USD/h 0.1528 USD/h
Eemshaven (NL) / europe-west4
0.0879 USD/h 0.1543 USD/h
St. Ghislain (BE) / europe-west1
0.0853 USD/h 0.1616 USD/h
Toronto (CA) / northamerica-northeast2
0.0919 USD/h 0.1616 USD/h
Montréal (CA) / northamerica-northeast1
0.0921 USD/h 0.1616 USD/h
Las Vegas (US) / us-west4
0.0942 USD/h 0.1653 USD/h
London (GB) / europe-west2
0.1003 USD/h 0.1671 USD/h
Changhua County (TW) / asia-east1
0.0923 USD/h 0.17 USD/h
Frankfurt (DE) / europe-west3
0.0984 USD/h 0.173 USD/h
Jurong West (SG) / asia-southeast1
0.1087 USD/h 0.1811 USD/h
Seoul (KR) / asia-northeast3
0.0613 USD/h 0.1885 USD/h
Tokyo (JP) / asia-northeast1
0.1074 USD/h 0.1885 USD/h
Zurich (CH) / europe-west6
0.1096 USD/h 0.1923 USD/h
Dammam (SA) / me-central2
0.1335 USD/h 0.2349 USD/h

Processor

vCPUs
4
CPU Allocation
Dedicated
CPU Cores
2
CPU Speed
2.2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU L1D Cache
32 KiB
CPU L1D Cache Total
64 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
64 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
2 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
2.6
Scalability
130

System Resources and Accelerators

MEMORY
Memory Amount
16 GiB
Memory Amount Actual
16 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 accelerator-focused virtual machine pairing dedicated Intel Xeon processors with an NVIDIA L4 GPU for high-efficiency machine learning inference.

    GPU AcceleratedGeneral Purpose

    Google Cloud Platform g2-standard-4 is a graphics-optimized instance featuring 4 dedicated vCPUs from an Intel Xeon x86_64 processor running at 2.2 GHz, paired with 16.0 GB of system memory. The server's defining feature is a bundled NVIDIA L4 GPU from the Ada Lovelace family, equipped with 22 GB of VRAM. While standard CPU, memory, and database benchmarks place this instance in the lower performance tiers, its GPU-accelerated capabilities deliver top-tier results for machine learning tasks. Specifically, LLM inference speeds for prompt processing and text generation on 135M and 7B models rank in the top 10%. With no local storage included, this instance is qualitatively cost-efficient for specialized workloads that offload processing to the GPU. It is highly suited for AI inference, graphics rendering, and lightweight machine learning deployments, rather than general-purpose or CPU-heavy computing.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    0.238Score
    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) 309,024 ops/sec 1,917,397 ops/sec 0.161 50.00% 50.00% -59.90%
    Redis RPS (pipeline=16, SET) 2,003,831 ops/sec 11,681,410 ops/sec 0.172 20.00% 20.00% -29.70%
    PassMark Memory Mark (composite) 1,836 2,418 0.759 10.00% 10.00% -2.72%
    Memory bandwidth (read, 16 MB ~ L3) 36,164 MB/sec 108,140 MB/sec 0.334 10.00% 10.00% -10.40%
    PassMark single-thread CPU 1,691 Mops/s 2,365 Mops/s 0.715 10.00% 10.00% -3.30%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,051

    Geekbench Multi-Core

    Score: 2,294

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 3754
    Compression
    		 47481
    Encryption
    		 1449
    Extended Instructions
    		 2901
    Floating Point Maths
    		 5668
    Integer Maths
    		 10529
    Physics
    		 508
    Prime Numbers
    		 23
    Single Threaded
    		 1691
    String Sorting
    		 5675

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 1836
    Database Operations
    		 1327
    Memory Latency
    		 52
    Memory Read Cached
    		 20540
    Memory Read Uncached
    		 11099
    Memory Write
    		 9910

    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-8 832 GiB1
    g2-standard-12 1248 GiB1
    g2-standard-16 1664 GiB1
    g2-standard-24 2496 GiB2
    g2-standard-32 32128 GiB1
    g2-standard-48 48192 GiB4
    g2-standard-96 96384 GiB8

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYGPUs

    g2-standard-4 FAQs