rtx5000-84 by OVHcloud

rtx5000-84 is a Cloud GPU (16 vCPUs, 84 GiB RAM, 400 GB SSD, 3xQuadro RTX 5000 16 GiB VRAM) server offered by OVHcloud with 16 vCPUs, 84 GiB of memory and 400 GB of storage. The pricing starts at 1.2042 USD per hour.
16 vCPU
84 GiB Memory
400 GB Storage
3 GPU
Spare SCore
22,027
(All-cores)
1,760
(Single-core)

Specifications

Server Metadata

Vendor ID
ovh
Name
rtx5000-84
Description
Cloud GPU (16 vCPUs, 84 GiB RAM, 400 GB SSD, 3xQuadro RTX 5000 16 GiB VRAM)
Family
Cloud GPU
Hw Virt
Status
active
Observed At
2026-10-27T15:34:10.027760

Availability

REGION / IDSPOTONDEMAND
GRA9 (FR) / GRA9
- 1.2042 USD/h

Processor

vCPUs
16
Hypervisor
KVM
CPU Allocation
Dedicated
CPU Cores
16
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
512 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
512 KiB
CPU L2 Cache
4 MiB
CPU L2 Cache Total
64 MiB
CPU L3 Cache
16 MiB
CPU L3 Cache Total
256 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
12.5
Scalability
78.12

System Resources and Accelerators

MEMORY
Memory Amount
84 GiB
Memory Amount Actual
82 GiB
ACCELERATORS
Accelerator Count
3
Accelerator Memory Min
16 GiB
Accelerator Memory Total
48 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)
  • NVIDIA Turing Quadro RTX 5000 (Memory amount: 15360, Firmware version: 590.48.01, BIOS version: 90.04.B7.00.04, Clock rate: 2100)
  • 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
10 Gbps
Network Speed Max
10 Gbps
Inbound Traffic
0 GB/month
Outbound Traffic
0 GB/month
IPv4
1

CPU and System Topology

Server Description

A dedicated multi-GPU server featuring three Turing-architecture graphics cards and 48 GB of total VRAM for accelerated parallel computing.

GPU AcceleratedCompute Optimized

The OVHcloud rtx5000-84 is a KVM-based server in the Cloud GPU family, configured with an Intel Xeon W-3235 processor featuring 16 dedicated physical cores running at 3.3 GHz. It is equipped with 84.0 GB of system memory, a 400 GB local SSD, and a 10 Gbps baseline network interface. The server's primary feature is its triple NVIDIA Quadro RTX 5000 GPU setup, providing a total of 48 GB of Turing-architecture VRAM. Benchmark results show top-tier performance in LLM inference, reaching 65.53 tokens/sec for text generation on a 7B model, alongside strong Passmark memory scores. However, single-threaded CPU tasks like gzip compression show weaker relative performance. This configuration is well-suited for GPU-accelerated workloads, including machine learning inference, ray tracing, and parallel data processing.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

1.1Score
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) 2,188,576 ops/sec 1,918,343 ops/sec 1.2 50.00% 50.00% +9.50%
Redis RPS (pipeline=16, SET) 11,976,938 ops/sec 11,704,734 ops/sec 1 20.00% 20.00% 0.00%
PassMark Memory Mark (composite) 2,913 2,416 1.2 10.00% 10.00% +1.80%
Memory bandwidth (read, 16 MB ~ L3) 103,848 MB/sec 108,420 MB/sec 0.91 10.00% 10.00% -0.94%
PassMark single-thread CPU 2,529 Mops/s 2,365 Mops/s 1 10.00% 10.00% 0.00%

GPU Bandwidth and Latency

Node (all GPUs)
Node baseline directional bandwidth
16.9 GB/s
Node GPU-to-host bandwidth
19.8 GB/s
Node host-to-GPU bandwidth
18.5 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
663 ns
Benchmark Environment
Driver Version
 535.274.02
CUDA Runtime Version
 12.6
nvbandwidth Version
 v0.5
GPU Count
 3
P2P Supported
No
Efficiency
SM/CE copy efficiency
1.00

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 1,473

Geekbench Multi-Core

Score: 8,459

Passmark CPU Scores

BENCHMARKSCORE
Mark
 20,743
Compression
 323,368
Encryption
 8,898
Extended Instructions
 22,326
Floating Point Maths
 43,035
Integer Maths
 67,889
Physics
 1,007
Prime Numbers
 67
Single Threaded
 2,529
String Sorting
 36,764

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2,913
Database Operations
 9,386
Memory Latency
 48
Memory Read Cached
 29,678
Memory Read Uncached
 12,978
Memory Write
 11,872

Stress-ng Stressors

CPU integerSingleMultiScaling
atomic
 267.98 246.53 0.92×
bitops
 135,565 1,567,550 11.56×
branch
 190,936 2,505,361 13.12×
funccall
 663.84 7,354 11.08×
funcret
 14,066 178,516 12.69×
hash
 156,081 1,971,288 12.63×
intmath
 27,402 358,096 13.07×
nop
 237,754 2,518,914 10.59×
prime
 386,231 4,451,768 11.53×
rotate
 121,003 1,496,184 12.36×
str
 916,762 10,349,733 11.29×
wcs
 595,952 6,220,545 10.44×
CryptographySingleMultiScaling
crypt
 3,004 33,302 11.09×
CompressionSingleMultiScaling
jpeg
 730.3 8,495 11.63×
zlib
 65.35 837.59 12.82×
HypervisorSingleMultiScaling
clock
 53,290 335,880 6.30×
clone
 465.47 3,930 8.44×
context
 5,519 71,314 12.92×
cpu-sched
 82.99 1,026 12.37×
eventfd
 68,401 831,776 12.16×
fault
 13,876 129,654 9.34×
fork
 1,612 40,305 25.00×
getrandom
 58,441 691,104 11.83×
hrtimers
 128,300 2,107,404 16.43×
mprotect
 1,151,867 5,149,340 4.47×
mtx
 6,253,317 430,434,760 68.83×
munmap
 1,013 29,976 29.60×
null
 779,097 8,971,862 11.52×
pipe
 910,983 6,280,815 6.89×
priv-instr
 376,875 4,381,410 11.63×
resched
 5,723,001 4,104,358 0.72×
switch
 205,483 1,980,649 9.64×
timermix
 263,087 3,155,964 12.00×
tlb-shootdown
 14,351 27,207 1.90×
tsc
 1,240,731 15,432,324 12.44×
usersyscall
 685,622 7,921,494 11.55×
vdso
 89,556,181 1,130,122,871 12.62×
vfork
 19,946 208,146 10.44×
x86syscall
 9,111,764 112,837,055 12.38×
yield
 14,941,607 14,844,504 0.99×
zero
 3,864,271 43,875,027 11.35×
CPU float/SIMDSingleMultiScaling
eigen
 20,256 234,846 11.59×
expmath
 3,359 43,115 12.83×
fma
 687,985 9,526,237 13.85×
fp
 152.64 1,816 11.90×
fractal
 6 77.43 12.91×
hyperbolic
 3,371 45,590 13.52×
logmath
 5,707 72,570 12.72×
matrix
 3,740 50,265 13.44×
matrix-3d
 567.51 1,471 2.59×
monte-carlo
 280.36 3,502 12.49×
mpfr
 1,509 17,198 11.39×
powmath
 1,971 25,698 13.04×
trig
 2,123 26,303 12.39×
veccmp
 19,654 216,655 11.02×
vecfp
 1,619 19,537 12.07×
vecmath
 2,660 35,994 13.53×
vecshuf
 706.55 7,995 11.32×
vecwide
 28,825 348,655 12.10×
AlgorithmsSingleMultiScaling
bitonicsort
 9 103.6 11.51×
bsearch
 294.74 3,390 11.50×
bubblesort
 1 9.6 9.60×
fibsearch
 302.09 3,532 11.69×
heapsort
 10.8 121.2 11.22×
hsearch
 5,992 69,260 11.56×
insertionsort
 10 107.6 10.76×
malloc
 2,724,132 26,207,266 9.62×
mcontend
 103.33 5,148 49.83×
mergesort
 29 347.39 11.98×
qsort
 18.6 212.8 11.44×
skiplist
 6,178 76,543 12.39×
tree
 1.6 9.8 6.13×
MemorySingleMultiScaling
cache
 278,668 874,915 3.14×
cachehammer
 505,268 6,738,447 13.34×
cacheline
 31.67 497.21 15.70×
l1cache
 284.82 3,233 11.35×
memcpy
 437.9 4,903 11.20×
memrate
 2.17 6.21 2.86×
memthrash
 201.04 401.92 2.00×
ptr-chase
 18,702,348 157,289,253 8.41×
spinmem
 286.38 894 3.12×
stream
 108.02 4,754 44.01×
vm
 121,748 294,308 2.42×

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
rtx5000-28 428 GiB1
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

Similar Servers

INSTANCEVENDORvCPUsMEMORYAccelerators

rtx5000-84 FAQs