logo

g2-standard-16 by Google Cloud Platform

g2-standard-16 is a Graphics Optimized: 1 NVIDIA L4 GPU, 16 vCPUs, 64GB RAM server offered by Google Cloud Platform with 16 vCPUs, 64 GiB of memory and 0 GB of storage. The pricing starts at 0.2251 USD per hour.
16 vCPU
64 GiB Memory
1 GPU
Spare SCore
12653
(All-cores)
1195
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1600016
Name
g2-standard-16
Description
Graphics Optimized: 1 NVIDIA L4 GPU, 16 vCPUs, 64GB RAM
Family
g2
Hw Virt
Average Time To Start
18
Status
active
Observed At
2026-07-20T23:38:39.714272

Availability

REGION / IDSPOTONDEMAND
Ashburn (US) / us-east4
0.258 USD/h 0.5852 USD/h
Council Bluffs (US) / us-central1
0.3301 USD/h 0.5872 USD/h
The Dalles (US) / us-west1
0.3301 USD/h 0.5872 USD/h
Moncks Corner (US) / us-east1
0.3301 USD/h 0.5872 USD/h
Mumbai (IN) / asia-south1
0.2695 USD/h 0.6112 USD/h
Eemshaven (NL) / europe-west4
0.3238 USD/h 0.6171 USD/h
St. Ghislain (BE) / europe-west1
0.297 USD/h 0.6465 USD/h
Montréal (CA) / northamerica-northeast1
0.341 USD/h 0.6465 USD/h
Toronto (CA) / northamerica-northeast2
0.3478 USD/h 0.6465 USD/h
Las Vegas (US) / us-west4
0.3842 USD/h 0.6613 USD/h
London (GB) / europe-west2
0.4011 USD/h 0.6685 USD/h
Changhua County (TW) / asia-east1
0.3214 USD/h 0.6799 USD/h
Frankfurt (DE) / europe-west3
0.4152 USD/h 0.692 USD/h
Jurong West (SG) / asia-southeast1
0.4347 USD/h 0.7244 USD/h
Seoul (KR) / asia-northeast3
0.2251 USD/h 0.754 USD/h
Tokyo (JP) / asia-northeast1
0.4524 USD/h 0.754 USD/h
Zurich (CH) / europe-west6
0.4455 USD/h 0.7692 USD/h
Dammam (SA) / me-central2
0.488 USD/h 0.9395 USD/h

Processor

vCPUs
16
CPU Allocation
Dedicated
CPU Cores
8
CPU Speed
2.2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU L1D Cache
32 KiB
CPU L1D Cache Total
256 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
256 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
8 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
10.6
Scalability
132.5

System Resources and Accelerators

MEMORY
Memory Amount
64 GiB
Memory Amount Actual
64 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

    A graphics-optimized virtual server combining dedicated Intel Xeon processors with an NVIDIA L4 GPU for accelerated machine learning inference.

    GPU AcceleratedGeneral Purpose

    Google Cloud Platform g2-standard-16 is a graphics-optimized instance featuring 16 dedicated Intel Xeon vCPUs, 64.0 GB of RAM, and a single NVIDIA L4 GPU with 22 GB of VRAM. It does not include local storage. While single-core CPU benchmarks are weak, ranking in the bottom 25%, its GPU-accelerated LLM inference performance for small and medium models ranks in the top 10% tier. This makes the instance qualitatively cost-efficient for machine learning and graphics workloads, despite CPU-bound performance tradeoffs.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    0.711Score
    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) 1,228,906 ops/sec 1,896,415 ops/sec 0.648 50.00% 50.00% -19.50%
    Redis RPS (pipeline=16, SET) 7,702,085 ops/sec 11,539,523 ops/sec 0.667 20.00% 20.00% -7.78%
    PassMark Memory Mark (composite) 2,521 2,411 1.05 10.00% 10.00% +0.49%
    Memory bandwidth (read, 16 MB ~ L3) 93,030 MB/sec 107,368 MB/sec 0.866 10.00% 10.00% -1.43%
    PassMark single-thread CPU 1,691 Mops/s 2,363 Mops/s 0.715 10.00% 10.00% -3.30%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,063

    Geekbench Multi-Core

    Score: 6,659

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		13538
    Compression
    		187062
    Encryption
    		5810
    Extended Instructions
    		11945
    Floating Point Maths
    		22743
    Integer Maths
    		42240
    Physics
    		1521
    Prime Numbers
    		76
    Single Threaded
    		1691
    String Sorting
    		22203

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		2521
    Database Operations
    		5263
    Memory Latency
    		52
    Memory Read Cached
    		20704
    Memory Read Uncached
    		11185
    Memory Write
    		10359

    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-24 2496 GiB2
    g2-standard-32 32128 GiB1
    g2-standard-48 48192 GiB4
    g2-standard-96 96384 GiB8

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYGPUs

    g2-standard-16 FAQs