g2-standard-48 by Google Cloud Platform
g2-standard-48 is a Graphics Optimized: 4 NVIDIA L4 GPUs, 48 vCPUs, 192GB RAM server offered by Google Cloud Platform with 48 vCPUs, 192 GiB of memory and 0 GB of storage. The pricing starts at 0.5581 USD per hour.
48 vCPU
192 GiB Memory
4 GPU
Spare SCore
37916
(All-cores)
(All-cores)
1196
(Single-core)
(Single-core)
Specifications
Server Metadata
Vendor ID | gcp |
Server ID | 1600048 |
Name | g2-standard-48 |
Description | Graphics Optimized: 4 NVIDIA L4 GPUs, 48 vCPUs, 192GB RAM |
Family | g2 |
Hw Virt | |
Status | active |
Observed At | 2026-06-23T16:08:09.543022 |
Availability
| REGION / ID | SPOT | ONDEMAND |
|---|---|---|
Ashburn (US) / us-east4 | 0.774 USD/h | 1.7557 USD/h |
Council Bluffs (US) / us-central1 | 0.8573 USD/h | 1.7615 USD/h |
The Dalles (US) / us-west1 | 0.8573 USD/h | 1.7615 USD/h |
Moncks Corner (US) / us-east1 | 0.8573 USD/h | 1.7615 USD/h |
Mumbai (IN) / asia-south1 | 0.8086 USD/h | 1.8336 USD/h |
Eemshaven (NL) / europe-west4 | 0.9715 USD/h | 1.8514 USD/h |
St. Ghislain (BE) / europe-west1 | 0.7713 USD/h | 1.9396 USD/h |
Montréal (CA) / northamerica-northeast1 | 0.9282 USD/h | 1.9396 USD/h |
Toronto (CA) / northamerica-northeast2 | 0.946 USD/h | 1.9396 USD/h |
Las Vegas (US) / us-west4 | 0.9975 USD/h | 1.984 USD/h |
London (GB) / europe-west2 | 1.102 USD/h | 2.0056 USD/h |
Changhua County (TW) / asia-east1 | 0.8346 USD/h | 2.0396 USD/h |
Frankfurt (DE) / europe-west3 | 1.0891 USD/h | 2.076 USD/h |
Jurong West (SG) / asia-southeast1 | 1.192 USD/h | 2.1732 USD/h |
Seoul (KR) / asia-northeast3 | 0.5581 USD/h | 2.2621 USD/h |
Tokyo (JP) / asia-northeast1 | 1.1871 USD/h | 2.2621 USD/h |
Zurich (CH) / europe-west6 | 1.2118 USD/h | 2.3077 USD/h |
Dammam (SA) / me-central2 | 1.2681 USD/h | 2.8184 USD/h |
Processor
vCPUs | 48 |
CPU Allocation | Dedicated |
CPU Cores | 24 |
CPU Speed | 2.2 GHz |
CPU Architecture | x86_64 |
CPU Manufacturer | Intel |
CPU Family | Xeon |
CPU L1D Cache | 32 KiB |
CPU L1D Cache Total | 768 KiB |
CPU L1I Cache | 32 KiB |
CPU L1I Cache Total | 768 KiB |
CPU L2 Cache | 1 MiB |
CPU L2 Cache Total | 24 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 | 31.7 |
Scalability | 132.08 |
System Resources and Accelerators
| MEMORY | |
|---|---|
Memory Amount | 192 GiB |
Memory Amount Actual | 192 GiB |
| GPU | |
|---|---|
GPU Count | 4 |
GPU Memory Min | 22 GiB |
GPU Memory Total | 90 GiB |
GPU Manufacturer | NVIDIA |
GPU Family | Ada Lovelace |
GPU Model | L4 |
GPUs |
|
| 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 quad-GPU accelerated server featuring Ada Lovelace architecture and 48 dedicated vCPUs, optimized for high-throughput language model inference.
GPU AcceleratedGeneral Purpose
Google Cloud Platform g2-standard-48 is a graphics-optimized server equipped with 4 NVIDIA L4 GPUs from the Ada Lovelace architecture, delivering 90 GB of total VRAM. The host system features 48 dedicated Intel Xeon vCPUs (24 physical cores) operating at 2.2 GHz and 192.0 GB of system memory, with no local storage included. Performance benchmarks indicate a significant divergence: single-core CPU capabilities are weak, ranking in the bottom 25%, while multi-core and memory bandwidth metrics remain average. However, the server achieves top-tier results in LLM inference, particularly for prompt processing and text generation across small, medium, and large models. This hardware profile is highly efficient for parallelized GPU workloads, machine learning inference, and graphics rendering, though it presents a tradeoff for applications reliant on high single-threaded CPU performance or local storage.
Economics
Performance
Memory Bandwidth
Compression
OpenSSL
Geekbench Single-Core
Score: 1,051
Geekbench Multi-Core
Score: 10,460
Passmark CPU Scores
| BENCHMARK | SCORE |
|---|---|
Mark | 31607 |
Compression | 548320 |
Encryption | 16611 |
Extended Instructions | 34890 |
Floating Point Maths | 67905 |
Integer Maths | 126890 |
Physics | 2474 |
Prime Numbers | 166 |
Single Threaded | 1703 |
String Sorting | 61440 |
Passmark Memory Scores
| BENCHMARK | SCORE |
|---|---|
Memory Mark | 2596 |
Database Operations | 15027 |
Memory Latency | 52 |
Memory Read Cached | 20570 |
Memory Read Uncached | 10704 |
Memory Write | 10150 |
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
| INSTANCE | vCPUs | MEMORY | GPUs |
|---|---|---|---|
| g2-standard-4 | 4 | 16 GiB | 1 |
| g2-standard-8 | 8 | 32 GiB | 1 |
| g2-standard-12 | 12 | 48 GiB | 1 |
| g2-standard-16 | 16 | 64 GiB | 1 |
| g2-standard-24 | 24 | 96 GiB | 2 |
| g2-standard-32 | 32 | 128 GiB | 1 |
| g2-standard-96 | 96 | 384 GiB | 8 |
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | GPUs |
|---|