t2-le-180 by OVHcloud

t2-le-180 is a Cloud GPU (60 vCPUs, 180 GiB RAM, 500 GB NVMe, 4xV100S 32 GiB VRAM) server offered by OVHcloud with 60 vCPUs, 180 GiB of memory and 500 GB of storage. The pricing starts at 3.575 USD per hour.
60 vCPU
180 GiB Memory
500 GB Storage
4 GPU
Spare SCore
59,632
(All-cores)
1,477
(Single-core)

Specifications

Server Metadata

Vendor ID
ovh
Name
t2-le-180
Description
Cloud GPU (60 vCPUs, 180 GiB RAM, 500 GB NVMe, 4xV100S 32 GiB VRAM)
Family
Cloud GPU
Hw Virt
Average Time To Start
184
Status
active
Observed At
2026-11-01T09:28:26.232208

Availability

REGION / IDSPOTONDEMAND
BHS5 (CA) / BHS5
- 3.575 USD/h
DE1 (DE) / DE1
- 3.575 USD/h
GRA11 (FR) / GRA11
- 3.575 USD/h
GRA7 (FR) / GRA7
- 3.575 USD/h
GRA9 (FR) / GRA9
- 3.575 USD/h
UK1 (GB) / UK1
- 3.575 USD/h
WAW1 (PL) / WAW1
- 3.575 USD/h

Processor

vCPUs
60
Hypervisor
KVM
CPU Allocation
Dedicated
CPU Cores
60
CPU Speed
2.9 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
6226R
CPU L1D Cache
32 KiB
CPU L1D Cache Total
2 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
2 MiB
CPU L2 Cache
4 MiB
CPU L2 Cache Total
240 MiB
CPU L3 Cache
16 MiB
CPU L3 Cache Total
960 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
40.4
Scalability
67.33

System Resources and Accelerators

MEMORY
Memory Amount
180 GiB
Memory Amount Actual
176 GiB
ACCELERATORS
Accelerator Count
4
Accelerator Memory Min
32 GiB
Accelerator Memory Total
128 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Volta
Accelerator Model
V100S
Accelerators
  • NVIDIA Volta Tesla V100S-PCIE-32GB (Memory amount: 32768, BIOS version: 88.00.98.00.01, Clock rate: 1597)
  • NVIDIA Volta Tesla V100S-PCIE-32GB (Memory amount: 32768, BIOS version: 88.00.98.00.01, Clock rate: 1597)
  • NVIDIA Volta Tesla V100S-PCIE-32GB (Memory amount: 32768, BIOS version: 88.00.98.00.01, Clock rate: 1597)
  • NVIDIA Volta Tesla V100S-PCIE-32GB (Memory amount: 32768, BIOS version: 88.00.98.00.01, Clock rate: 1597)
STORAGE
Storage Size
500 GB
Storage Type
nvme ssd
Storages
  • 500 GB nvme ssd
NETWORK
Network Speed Baseline
10 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 multi-GPU server featuring sixty physical cores and four accelerators for intensive machine learning and parallel computing workloads.

GPU AcceleratedCompute OptimizedStorage & Database

The OVHcloud t2-le-180 is a dedicated GPU-accelerated server built on the KVM hypervisor. It features 60 physical cores from Intel Xeon 6226R processors clocked at 2.9 GHz, paired with 180 GB of system memory and a 500 GB NVMe SSD. The server's primary strength lies in its graphics hardware, which consists of four NVIDIA Volta V100S GPUs providing a total of 128 GB of VRAM. Network performance is supported by a 10 Gbps baseline. In benchmark testing, the t2-le-180 delivers top-tier performance in LLM inference, achieving 1277.99 tokens/sec for 7B model prompt processing and 120.29 tokens/sec for text generation. This hardware configuration is highly efficient for parallel computing, machine learning, and deep learning workloads.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

1.7Score
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) 4,108,032 ops/sec 1,918,343 ops/sec 2.2 50.00% 50.00% +48.00%
Redis RPS (pipeline=16, SET) 26,804,047 ops/sec 11,704,734 ops/sec 2.2 20.00% 20.00% +17.00%
PassMark Memory Mark (composite) 2,795 2,416 1.2 10.00% 10.00% +1.80%
Memory bandwidth (read, 16 MB ~ L3) 111,383 MB/sec 108,466 MB/sec 1 10.00% 10.00% 0.00%
PassMark single-thread CPU 2,148 Mops/s 2,365 Mops/s 0.88 10.00% 10.00% -1.30%

GPU Bandwidth and Latency

Node (all GPUs)
Node baseline directional bandwidth
43.0 GB/s
Node GPU-to-host bandwidth
47.8 GB/s
Node host-to-GPU bandwidth
44.6 GB/s
Single GPU slot
Per-GPU GPU-to-host bandwidth
12.2 GB/s
Per-GPU host-to-GPU bandwidth
11.7 GB/s
Per-GPU host-device latency
717 ns
Per-GPU device memory copy bandwidth
514.2 GB/s
Benchmark Environment
Driver Version
 580.178.04
CUDA Version (driver)
 13.0
nvbandwidth Version
 v0.8
GPU Count
 4
P2P Supported
No
Efficiency
SM/CE copy efficiency
0.49

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 1,239

Geekbench Multi-Core

Score: 10,938

Passmark CPU Scores

BENCHMARKSCORE
Mark
 42,630
Compression
 829,445
Encryption
 24,802
Extended Instructions
 52,461
Floating Point Maths
 111,066
Integer Maths
 201,079
Physics
 1,968
Prime Numbers
 150
Single Threaded
 2,148
String Sorting
 84,181

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2,795
Database Operations
 16,513
Memory Latency
 51
Memory Read Cached
 25,339
Memory Read Uncached
 11,919
Memory Write
 10,390

Stress-ng Stressors

CPU integerSingleMultiScaling
atomic
 253.38 168.64 0.67×
bitops
 114,441 3,989,005 34.86×
branch
 163,568 7,454,689 45.58×
funccall
 574.3 17,282 30.09×
funcret
 12,041 489,086 40.62×
hash
 133,558 5,646,438 42.28×
intmath
 23,453 1,040,926 44.38×
nop
 202,550 5,696,031 28.12×
prime
 331,132 10,774,134 32.54×
rotate
 102,380 4,485,139 43.81×
str
 790,689 11,779,218 14.90×
wcs
 488,822 14,922,189 30.53×
CryptographySingleMultiScaling
crypt
 2,591 75,744 29.23×
CompressionSingleMultiScaling
jpeg
 634.17 19,795 31.21×
zlib
 60.47 2,326 38.46×
HypervisorSingleMultiScaling
clock
 38,042 146,754 3.86×
clone
 300.59 5,021 16.70×
context
 4,647 206,737 44.49×
cpu-sched
 64.73 3,894 60.15×
eventfd
 72,971 1,517,753 20.80×
fault
 11,289 92,689 8.21×
fork
 2,814 53,352 18.96×
getrandom
 46,655 1,587,911 34.04×
hrtimers
 234,272 7,125,273 30.41×
mprotect
 600,101 10,661,348 17.77×
mtx
 7,234,320 1,392,389,500 192.47×
munmap
 2,079 50,148 24.12×
null
 681,447 24,164,908 35.46×
pipe
 848,243 11,960,571 14.10×
priv-instr
 312,423 9,460,975 30.28×
resched
 3,182,846 10,412,230 3.27×
switch
 155,005 4,866,037 31.39×
timermix
 234,217 9,519,816 40.65×
tlb-shootdown
 9,664 58,393 6.04×
tsc
 1,044,833 43,226,744 41.37×
usersyscall
 562,618 12,353,142 21.96×
vdso
 72,937,528 2,773,644,928 38.03×
vfork
 19,080 103,063 5.40×
x86syscall
 7,992,002 304,353,812 38.08×
yield
 34,902,206 45,745,125 1.31×
zero
 3,231,767 116,842,680 36.15×
CPU float/SIMDSingleMultiScaling
eigen
 17,160 598,261 34.86×
expmath
 2,840 122,860 43.26×
fma
 588,460 28,944,619 49.19×
fp
 136.8 4,763 34.81×
fractal
 5.2 217.52 41.83×
hyperbolic
 2,949 131,353 44.54×
logmath
 4,768 201,927 42.35×
matrix
 3,189 145,447 45.61×
matrix-3d
 560.75 2,699 4.81×
monte-carlo
 246.75 7,515 30.46×
mpfr
 1,286 37,051 28.81×
powmath
 1,682 72,062 42.85×
trig
 1,814 65,829 36.28×
veccmp
 16,652 487,243 29.26×
vecfp
 1,384 52,771 38.14×
vecmath
 2,323 102,695 44.20×
vecshuf
 599.17 19,240 32.11×
vecwide
 24,191 840,844 34.76×
AlgorithmsSingleMultiScaling
bitonicsort
 7.6 247.19 32.52×
bsearch
 253.63 8,569 33.79×
bubblesort
 0.8 24.4 30.50×
fibsearch
 259.27 9,168 35.36×
heapsort
 9.2 319.19 34.69×
hsearch
 5,322 187,790 35.28×
insertionsort
 8.6 250.2 29.09×
malloc
 1,995,335 46,655,188 23.38×
mcontend
 67.46 15,251 226.07×
mergesort
 24.6 745.8 30.32×
qsort
 15.8 509.57 32.25×
skiplist
 5,179 211,994 40.93×
tree
 1.4 24.35 17.39×
MemorySingleMultiScaling
cache
 437,120 912,563 2.09×
cachehammer
 391,681 12,538,352 32.01×
cacheline
 9.77 1,396 142.93×
l1cache
 240.54 7,868 32.71×
memcpy
 368.8 11,342 30.75×
memrate
 1.18 10.53 8.92×
memthrash
 190.87 690.64 3.62×
ptr-chase
 30,230,041 378,668,897 12.53×
spinmem
 252.79 2,856 11.30×
stream
 78.09 29,923 383.18×
vm
 56,375 300,950 5.34×

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
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

t2-le-180 FAQs