t2-le-45 by OVHcloud

t2-le-45 is a Cloud GPU (15 vCPUs, 45 GiB RAM, 300 GB NVMe, 1xV100S 32 GiB VRAM) server offered by OVHcloud with 15 vCPUs, 45 GiB of memory and 300 GB of storage. The pricing starts at 0.923 USD per hour.
15 vCPU
45 GiB Memory
300 GB Storage
1 GPU
Spare SCore
22,299
(All-cores)
1,490
(Single-core)

Specifications

Server Metadata

Vendor ID
ovh
Name
t2-le-45
Description
Cloud GPU (15 vCPUs, 45 GiB RAM, 300 GB NVMe, 1xV100S 32 GiB VRAM)
Family
Cloud GPU
Hw Virt
Average Time To Start
218
Status
active
Observed At
2026-09-17T00:43:22.734411

Availability

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

Processor

vCPUs
15
Hypervisor
KVM
CPU Allocation
Dedicated
CPU Cores
15
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
480 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
480 KiB
CPU L2 Cache
4 MiB
CPU L2 Cache Total
60 MiB
CPU L3 Cache
16 MiB
CPU L3 Cache Total
240 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
15
Scalability
100

System Resources and Accelerators

MEMORY
Memory Amount
45 GiB
Memory Amount Actual
44 GiB
GPU
GPU Count
1
GPU Memory Min
32 GiB
GPU Memory Total
32 GiB
GPU Manufacturer
NVIDIA
GPU Family
Volta
GPU Model
V100S
GPUs
  • NVIDIA Volta Tesla V100S-PCIE-32GB (Memory amount: 32768, BIOS version: 88.00.98.00.01, Clock rate: 1597)
STORAGE
Storage Size
300 GB
Storage Type
nvme ssd
Storages
  • 300 GB nvme 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 fifteen-core virtual server featuring an NVIDIA Volta GPU with thirty-two gigabytes of VRAM for accelerated machine learning inference.

GPU AcceleratedCompute Optimized

OVHcloud t2-le-45 is a KVM-based virtual server in the Cloud GPU family, designed for accelerated compute workloads. It is configured with a dedicated Intel Xeon 6226R processor offering 15 physical cores at 2.9 GHz, 45 GB of RAM, and a 300 GB NVMe SSD. Acceleration is driven by a single NVIDIA Volta V100S GPU with 32 GB of VRAM. While standard CPU and memory benchmarks sit in the average tier, the server excels in GPU-driven tasks. LLM inference benchmarks show top-tier performance, processing 1434.01 tokens per second for prompt processing and 124.44 tokens per second for text generation on a medium 7B model. This hardware profile makes the t2-le-45 a cost-efficient option for machine learning inference, data science, and parallel processing workloads that require dedicated CPU cores and high VRAM without the premium cost of newer GPU generations.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

1.13Score
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) 2,321,695 ops/sec 1,919,696 ops/sec 1.21 50.00% 50.00% +10.00%
Redis RPS (pipeline=16, SET) 13,570,928 ops/sec 11,736,081 ops/sec 1.16 20.00% 20.00% +3.01%
PassMark Memory Mark (composite) 2,613 2,418 1.08 10.00% 10.00% +0.77%
Memory bandwidth (read, 16 MB ~ L3) 113,981 MB/sec 108,260 MB/sec 1.05 10.00% 10.00% +0.49%
PassMark single-thread CPU 2,118 Mops/s 2,365 Mops/s 0.896 10.00% 10.00% -1.09%

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 1,224

Geekbench Multi-Core

Score: 9,126

Passmark CPU Scores

BENCHMARKSCORE
Mark
 22173
Compression
 327024
Encryption
 8312
Extended Instructions
 23537
Floating Point Maths
 46173
Integer Maths
 64683
Physics
 2303
Prime Numbers
 168
Single Threaded
 2118
String Sorting
 39327

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2613
Database Operations
 9525
Memory Latency
 52
Memory Read Cached
 25589
Memory Read Uncached
 10918
Memory Write
 10409

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

INSTANCEvCPUsMEMORYGPUs
rtx5000-28 428 GiB1
t1-le-45 845 GiB1
rtx5000-56 856 GiB2
l40s-90 1590 GiB1
a100-180 15180 GiB1
t1-le-90 1690 GiB2
rtx5000-84 1684 GiB3

Similar Servers

INSTANCEVENDORvCPUsMEMORYGPUs

t2-le-45 FAQs