logo

g2-standard-12 by Google Cloud Platform

g2-standard-12 is a Graphics Optimized: 1 NVIDIA L4 GPU, 12 vCPUs, 48GB RAM server offered by Google Cloud Platform with 12 vCPUs, 48 GiB of memory and 0 GB of storage. The pricing starts at 0.2042 USD per hour.
12 vCPU
48 GiB Memory
1 GPU
Spare SCore
9484
(All-cores)
1198
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1600012
Name
g2-standard-12
Description
Graphics Optimized: 1 NVIDIA L4 GPU, 12 vCPUs, 48GB RAM
Family
g2
Hw Virt
Average Time To Start
170
Status
active
Observed At
2026-08-11T00:56:01.955602

Availability

REGION / IDSPOTONDEMAND
Ashburn (US) / us-east4
0.2129 USD/h 0.4389 USD/h
Council Bluffs (US) / us-central1
0.2642 USD/h 0.4404 USD/h
The Dalles (US) / us-west1
0.2642 USD/h 0.4404 USD/h
Moncks Corner (US) / us-east1
0.2642 USD/h 0.4404 USD/h
Mumbai (IN) / asia-south1
0.2224 USD/h 0.4584 USD/h
Eemshaven (NL) / europe-west4
0.2777 USD/h 0.4629 USD/h
St. Ghislain (BE) / europe-west1
0.2573 USD/h 0.4849 USD/h
Montréal (CA) / northamerica-northeast1
0.291 USD/h 0.4849 USD/h
Toronto (CA) / northamerica-northeast2
0.291 USD/h 0.4849 USD/h
Las Vegas (US) / us-west4
0.2976 USD/h 0.496 USD/h
London (GB) / europe-west2
0.3008 USD/h 0.5014 USD/h
Changhua County (TW) / asia-east1
0.2784 USD/h 0.5099 USD/h
Frankfurt (DE) / europe-west3
0.3114 USD/h 0.519 USD/h
Jurong West (SG) / asia-southeast1
0.326 USD/h 0.5433 USD/h
Seoul (KR) / asia-northeast3
0.2042 USD/h 0.5655 USD/h
Tokyo (JP) / asia-northeast1
0.3393 USD/h 0.5655 USD/h
Zurich (CH) / europe-west6
0.3461 USD/h 0.5769 USD/h
Dammam (SA) / me-central2
0.4228 USD/h 0.7046 USD/h

Processor

vCPUs
12
CPU Allocation
Dedicated
CPU Cores
6
CPU Speed
2.2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU L1D Cache
32 KiB
CPU L1D Cache Total
192 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
192 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
6 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
7.9
Scalability
131.67

System Resources and Accelerators

MEMORY
Memory Amount
48 GiB
Memory Amount Actual
48 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 machine featuring dedicated GPU acceleration for efficient small and medium large language model inference.

    GPU AcceleratedGeneral Purpose

    Google Cloud Platform g2-standard-12 is a graphics-optimized virtual machine featuring 12 vCPUs from an Intel Xeon x86_64 processor, 48.0 GB of system memory, and a dedicated NVIDIA Ada Lovelace L4 GPU with 22 GB of VRAM. While single-core CPU benchmarks are weak, the instance delivers top-tier performance in small and medium LLM inference tasks, processing up to 11875.13 tokens per second for a 135M model. Multi-core performance and memory bandwidth remain average. Lacking local storage, this server is qualitatively cost-efficient for GPU-centric workloads that do not require high single-threaded CPU performance. It is best suited for LLM inference, image processing, and ray tracing.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    0.564Score
    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) 924,163 ops/sec 1,910,660 ops/sec 0.484 50.00% 50.00% -30.40%
    Redis RPS (pipeline=16, SET) 5,796,044 ops/sec 11,608,287 ops/sec 0.499 20.00% 20.00% -13.00%
    PassMark Memory Mark (composite) 2,409 2,416 0.997 10.00% 10.00% -0.03%
    Memory bandwidth (read, 16 MB ~ L3) 75,077 MB/sec 107,896 MB/sec 0.696 10.00% 10.00% -3.56%
    PassMark single-thread CPU 1,695 Mops/s 2,364 Mops/s 0.717 10.00% 10.00% -3.27%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,063

    Geekbench Multi-Core

    Score: 5,383

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 10478
    Compression
    		 139689
    Encryption
    		 4346
    Extended Instructions
    		 8971
    Floating Point Maths
    		 17053
    Integer Maths
    		 31706
    Physics
    		 1179
    Prime Numbers
    		 61
    Single Threaded
    		 1695
    String Sorting
    		 16728

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2409
    Database Operations
    		 3900
    Memory Latency
    		 52
    Memory Read Cached
    		 20776
    Memory Read Uncached
    		 10477
    Memory Write
    		 9783

    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-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-12 FAQs