g3.4xlarge by Amazon Web Services

g3.4xlarge is a Graphics intensive Gen3 4xlarge server offered by Amazon Web Services with 16 vCPUs, 122 GiB of memory and 0 GB of storage. The last known price was 0.1833 USD per hour.
16 vCPU
122 GiB Memory
1 Accelerator
Spare SCore
8,264
(All-cores)
881
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
g3.4xlarge
Description
Graphics intensive Gen3 4xlarge
Family
g3
Hw Virt
-
Status
inactive
Observed At
2026-10-27T18:18:33.882421

Availability

REGION / IDSPOTONDEMAND
Oregon (US) / us-west-2
0.350333 USD/h 1.14 USD/h
Northern Virgina (US) / us-east-1
0.494275 USD/h 1.14 USD/h
Ohio (US) / us-east-2
0.54395 USD/h 1.14 USD/h
Dublin (IE) / eu-west-1
0.54745 USD/h 1.21 USD/h
Quebec (CA) / ca-central-1
0.5564 USD/h 1.416 USD/h
Seoul (KR) / ap-northeast-2
0.1891 USD/h 1.42 USD/h
Frankfurt (DE) / eu-central-1
0.4747 USD/h 1.425 USD/h
London (GB) / eu-west-2
0.53675 USD/h 1.429 USD/h
California (US) / us-west-1
0.58095 USD/h 1.534 USD/h
Tokyo (JP) / ap-northeast-1
0.8086 USD/h 1.58 USD/h
Singapore (SG) / ap-southeast-1
0.5261 USD/h 1.67 USD/h
Sydney (AU) / ap-southeast-2
0.59755 USD/h 1.754 USD/h

Processor

vCPUs
16
Hypervisor
xen
CPU Allocation
Dedicated
CPU Cores
8
CPU Speed
2.7 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
E5-2686 v4
CPU L1D Cache
32 KiB
CPU L1D Cache Total
256 KiB
CPU L2 Cache
256 KiB
CPU L2 Cache Total
2 MiB
CPU L3 Cache Total
45 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, ht, syscall, nx, pdpe1gb, rdtscp, lm, constant_tsc, rep_good, nopl, xtopology, nonstop_tsc, cpuid, aperfmperf, tsc_known_freq, pni, pclmulqdq, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, tsc_deadline_timer, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, cpuid_fault, pti, fsgsbase, bmi1, hle, avx2, smep, bmi2, erms, invpcid, rtm, rdseed, adx, xsaveopt

System Resources and Accelerators

MEMORY
Memory Amount
122 GiB
ACCELERATORS
Accelerator Count
1
Accelerator Memory Min
8 GiB
Accelerator Memory Total
8 GiB
Accelerator Manufacturer
NVIDIA
Accelerator Family
Maxwell
Accelerator Model
M60
Accelerators
  • NVIDIA Maxwell Tesla M60 (Memory amount: 7680, BIOS version: 84.04.A6.00.01, Clock rate: 1177)
STORAGE
Storage Size
0 GB
Storages
    NETWORK
    Network Speed Baseline
    5 Gbps
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    0.61Score
    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) 1,061,445 ops/sec 1,918,343 ops/sec 0.58 50.00% 50.00% -24.00%
    Redis RPS (pipeline=16, SET) 6,644,665 ops/sec 11,704,734 ops/sec 0.55 20.00% 20.00% -11.00%
    PassMark Memory Mark (composite) 2,255 2,416 0.96 10.00% 10.00% -0.41%
    Memory bandwidth (read, 16 MB ~ L3) 59,443 MB/sec 108,420 MB/sec 0.54 10.00% 10.00% -6.00%
    PassMark single-thread CPU 1,740 Mops/s 2,365 Mops/s 0.71 10.00% 10.00% -3.40%

    GPU Bandwidth and Latency

    Node (all GPUs)
    Node baseline directional bandwidth
    		10.9 GB/s
    Node GPU-to-host bandwidth
    		13.2 GB/s
    Node host-to-GPU bandwidth
    		11.8 GB/s
    Single GPU slot
    Per-GPU GPU-to-host bandwidth
    		12.7 GB/s
    Per-GPU host-to-GPU bandwidth
    		9.1 GB/s
    Per-GPU host-device latency
    		990 ns
    Benchmark Environment
    Driver Version
    		 535.183.01
    CUDA Runtime Version
    		 12.6
    nvbandwidth Version
    		 v0.5
    GPU Count
    		 1
    P2P Supported
    No
    Efficiency
    SM/CE copy efficiency
    		1.00

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 910

    Geekbench Multi-Core

    Score: 5,547

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 11,932
    Compression
    		 172,650
    Encryption
    		 3,762
    Extended Instructions
    		 8,754
    Floating Point Maths
    		 24,464
    Integer Maths
    		 38,774
    Physics
    		 1,261
    Prime Numbers
    		 85
    Single Threaded
    		 1,740
    String Sorting
    		 25,472

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2,255
    Database Operations
    		 4,732
    Memory Latency
    		 54
    Memory Read Cached
    		 19,561
    Memory Read Uncached
    		 10,104
    Memory Write
    		 7,078

    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

    INSTANCEvCPUsMEMORYAccelerators

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    g3.4xlarge FAQs