rtx5000-28 by OVHcloud

rtx5000-28 is a Cloud GPU (4 vCPUs, 28 GiB RAM, 400 GB SSD, 1xQuadro RTX 5000 16 GiB VRAM) server offered by OVHcloud with 4 vCPUs, 28 GiB of memory and 400 GB of storage. The pricing starts at 0.4022 USD per hour.
4 vCPU
28 GiB Memory
400 GB Storage
1 GPU
Spare SCore
6,704
(All-cores)
1,745
(Single-core)

Specifications

Server Metadata

Vendor ID
ovh
Name
rtx5000-28
Description
Cloud GPU (4 vCPUs, 28 GiB RAM, 400 GB SSD, 1xQuadro RTX 5000 16 GiB VRAM)
Family
Cloud GPU
Hw Virt
Average Time To Start
92.33
Status
active
Observed At
2026-10-30T16:48:41.115660

Availability

REGION / IDSPOTONDEMAND
GRA9 (FR) / GRA9
- 0.4022 USD/h

Processor

vCPUs
4
Hypervisor
KVM
CPU Allocation
Dedicated
CPU Cores
4
CPU Speed
3.3 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
W-3235
CPU L1D Cache
32 KiB
CPU L1D Cache Total
128 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
128 KiB
CPU L2 Cache
4 MiB
CPU L2 Cache Total
16 MiB
CPU L3 Cache
16 MiB
CPU L3 Cache Total
64 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, syscall, nx, pdpe1gb, rdtscp, lm, constant_tsc, arch_perfmon, rep_good, nopl, xtopology, cpuid, tsc_known_freq, pni, pclmulqdq, vmx, ssse3, fma, cx16, pdcm, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, tsc_deadline_timer, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, cpuid_fault, ssbd, ibrs, ibpb, stibp, ibrs_enhanced, tpr_shadow, flexpriority, ept, vpid, ept_ad, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, erms, invpcid, mpx, avx512f, avx512dq, rdseed, adx, smap, clflushopt, clwb, avx512cd, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, arat, vnmi, umip, pku, ospke, avx512_vnni, md_clear, arch_capabilities
Ecpus
3.8
Scalability
95

System Resources and Accelerators

MEMORY
Memory Amount
28 GiB
Memory Amount Actual
27 GiB
ACCELERATORS
Accelerator Count
1
Accelerator Memory Min
16 GiB
Accelerator Memory Total
16 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Turing
Accelerator Model
RTX 5000
Accelerators
  • NVIDIA Turing Quadro RTX 5000 (Memory amount: 15360, Firmware version: 590.48.01, BIOS version: 90.04.B7.00.04, Clock rate: 2100)
STORAGE
Storage Size
400 GB
Storage Type
ssd
Storages
  • 400 GB ssd
NETWORK
Network Speed Baseline
2 Gbps
Network Speed Max
4 Gbps
Inbound Traffic
0 GB/month
Outbound Traffic
0 GB/month
IPv4
1

CPU and System Topology

Server Description

A dedicated GPU-accelerated virtual server featuring Turing architecture and local SSD storage for efficient machine learning inference.

GPU AcceleratedGeneral Purpose

OVHcloud rtx5000-28 is a KVM-based virtual server in the Cloud GPU family, powered by an Intel Xeon W-3235 processor with 4 dedicated physical cores at 3.3 GHz and 28 GB of RAM. It features a dedicated NVIDIA Quadro RTX 5000 GPU with 16 GB of VRAM, alongside 400 GB of local SSD storage and a 2 Gbps baseline network bandwidth. Benchmark data highlights top-tier performance in LLM inference for small and medium models, processing up to 10592.7 tokens per second. However, multi-core CPU performance and memory write speeds are relatively weak. This server is highly suited for machine learning inference, GPU-accelerated development, and moderate parallel computing workloads, offering a cost-effective GPU-enabled profile while presenting tradeoffs in heavy multi-threaded CPU tasks.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

0.47Score
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) 750,201 ops/sec 1,919,289 ops/sec 0.39 50.00% 50.00% -38.00%
Redis RPS (pipeline=16, SET) 4,604,737 ops/sec 11,728,058 ops/sec 0.38 20.00% 20.00% -18.00%
PassMark Memory Mark (composite) 2,524 2,416 1 10.00% 10.00% 0.00%
Memory bandwidth (read, 16 MB ~ L3) 45,901 MB/sec 108,466 MB/sec 0.42 10.00% 10.00% -8.30%
PassMark single-thread CPU 2,524 Mops/s 2,365 Mops/s 1 10.00% 10.00% 0.00%

GPU Bandwidth and Latency

Node (all GPUs)
Node baseline directional bandwidth
5.7 GB/s
Node GPU-to-host bandwidth
6.6 GB/s
Node host-to-GPU bandwidth
6.2 GB/s
Single GPU slot
Per-GPU GPU-to-host bandwidth
6.6 GB/s
Per-GPU host-to-GPU bandwidth
6.2 GB/s
Per-GPU host-device latency
655 ns
Benchmark Environment
Driver Version
 535.274.02
CUDA Version (driver)
 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: 1,434

Geekbench Multi-Core

Score: 4,162

Passmark CPU Scores

BENCHMARKSCORE
Mark
 7,501
Compression
 98,436
Encryption
 2,496
Extended Instructions
 7,181
Floating Point Maths
 13,966
Integer Maths
 19,572
Physics
 720
Prime Numbers
 47
Single Threaded
 2,524
String Sorting
 12,096

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2,524
Database Operations
 3,431
Memory Latency
 50
Memory Read Cached
 29,141
Memory Read Uncached
 11,756
Memory Write
 11,617

Stress-ng Stressors

CPU integerSingleMultiScaling
atomic
 270.2 278.7 1.03×
bitops
 134,071 505,257 3.77×
branch
 189,960 725,305 3.82×
funccall
 667.63 2,575 3.86×
funcret
 14,131 52,832 3.74×
hash
 153,710 590,758 3.84×
intmath
 27,378 104,888 3.83×
nop
 235,712 896,625 3.80×
prime
 381,731 1,465,523 3.84×
rotate
 114,938 453,405 3.94×
str
 887,181 3,529,011 3.98×
wcs
 599,452 2,214,208 3.69×
CryptographySingleMultiScaling
crypt
 2,984 11,469 3.84×
CompressionSingleMultiScaling
jpeg
 741.2 2,806 3.79×
zlib
 67.13 229.28 3.42×
HypervisorSingleMultiScaling
clock
 53,118 159,523 3.00×
clone
 432.72 1,227 2.83×
context
 5,452 20,729 3.80×
cpu-sched
 59.98 260.75 4.35×
eventfd
 61,895 383,706 6.20×
fault
 12,296 45,178 3.67×
fork
 2,511 17,824 7.10×
getrandom
 57,213 217,629 3.80×
hrtimers
 235,693 689,384 2.92×
mprotect
 1,153,997 1,730,160 1.50×
mtx
 7,797,691 151,658,143 19.45×
munmap
 1,166 12,356 10.60×
null
 753,137 2,935,635 3.90×
pipe
 951,362 2,999,025 3.15×
priv-instr
 357,417 1,358,919 3.80×
resched
 1,945,844 934,194 0.48×
switch
 102,059 1,022,632 10.02×
timermix
 261,326 899,275 3.44×
tlb-shootdown
 11,627 18,750 1.61×
tsc
 1,221,487 4,625,363 3.79×
usersyscall
 685,362 2,441,396 3.56×
vdso
 89,074,145 335,997,649 3.77×
vfork
 24,208 100,878 4.17×
x86syscall
 9,243,459 34,709,857 3.76×
yield
 4,842,474 4,719,561 0.97×
zero
 3,728,957 14,350,697 3.85×
CPU float/SIMDSingleMultiScaling
eigen
 19,185 74,790 3.90×
expmath
 3,256 12,362 3.80×
fma
 673,283 2,616,288 3.89×
fp
 148.8 565.16 3.80×
fractal
 6 22.6 3.77×
hyperbolic
 3,478 13,119 3.77×
logmath
 5,560 21,706 3.90×
matrix
 3,672 14,220 3.87×
matrix-3d
 568.04 1,364 2.40×
monte-carlo
 280.49 1,066 3.80×
mpfr
 1,503 5,718 3.81×
powmath
 1,948 7,453 3.83×
trig
 2,078 7,989 3.84×
veccmp
 19,173 73,393 3.83×
vecfp
 1,584 6,108 3.86×
vecmath
 2,722 10,247 3.76×
vecshuf
 679.86 2,660 3.91×
vecwide
 29,060 111,217 3.83×
AlgorithmsSingleMultiScaling
bitonicsort
 9 33.8 3.76×
bsearch
 298.28 1,128 3.78×
bubblesort
 1 3.2 3.20×
fibsearch
 286.87 1,130 3.94×
heapsort
 10.2 38.8 3.80×
hsearch
 6,034 23,542 3.90×
insertionsort
 10.2 38 3.73×
malloc
 2,440,648 11,373,665 4.66×
mcontend
 158.36 1,290 8.14×
mergesort
 29 109.8 3.79×
qsort
 18.4 69.8 3.79×
skiplist
 6,065 22,830 3.76×
tree
 1.6 4.8 3.00×
MemorySingleMultiScaling
cache
 220,785 470,002 2.13×
cachehammer
 447,002 1,829,881 4.09×
cacheline
 26.42 111.27 4.21×
l1cache
 273.29 1,059 3.87×
memcpy
 427.35 1,627 3.81×
memrate
 1.98 5.52 2.79×
memthrash
 122.75 217.82 1.77×
ptr-chase
 18,961,048 51,713,641 2.73×
spinmem
 289.39 220.76 0.76×
stream
 110.7 1,282 11.58×
vm
 117,402 291,510 2.48×

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

PostgreSQL heavy read-only throughput

Alternatives

Servers of the Same Family

INSTANCEvCPUsMEMORYAccelerators
t1-le-45 845 GiB1
rtx5000-56 856 GiB2
t2-le-45 1545 GiB1
l40s-90 1590 GiB1
a100-180 15180 GiB1
t1-le-90 1690 GiB2
rtx5000-84 1684 GiB3

Similar Servers

INSTANCEVENDORvCPUsMEMORYAccelerators

rtx5000-28 FAQs