a10-45 by OVHcloud

a10-45 is a Cloud GPU (30 vCPUs, 42 GiB RAM, 400 GB SSD, 1xA10 24 GiB VRAM) server offered by OVHcloud with 30 vCPUs, 42 GiB of memory and 400 GB of storage. The pricing starts at 0.8768 USD per hour.
30 vCPU
42 GiB Memory
400 GB Storage
1 GPU
Spare SCore
93,543
(All-cores)
3,108
(Single-core)

Specifications

Server Metadata

Vendor ID
ovh
Name
a10-45
Description
Cloud GPU (30 vCPUs, 42 GiB RAM, 400 GB SSD, 1xA10 24 GiB VRAM)
Family
Cloud GPU
Hw Virt
Average Time To Start
69
Status
active
Observed At
2026-09-16T12:53:33.073818

Availability

REGION / IDSPOTONDEMAND
GRA11 (FR) / GRA11
- 0.8768 USD/h
GRA9 (FR) / GRA9
- 0.8768 USD/h

Processor

vCPUs
30
Hypervisor
KVM
CPU Allocation
Dedicated
CPU Cores
30
CPU Speed
3.3 GHz
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
9554
CPU L1D Cache
64 KiB
CPU L1D Cache Total
2 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
2 MiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
15 MiB
CPU L3 Cache
16 MiB
CPU L3 Cache Total
480 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, syscall, nx, mmxext, fxsr_opt, pdpe1gb, rdtscp, lm, rep_good, nopl, cpuid, extd_apicid, 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, cmp_legacy, svm, cr8_legacy, abm, sse4a, misalignsse, 3dnowprefetch, osvw, perfctr_core, ssbd, ibrs, ibpb, stibp, vmmcall, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, erms, invpcid, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, avx512_bf16, clzero, xsaveerptr, wbnoinvd, arat, npt, lbrv, nrip_save, tsc_scale, vmcb_clean, pausefilter, pfthreshold, v_vmsave_vmload, vgif, avx512vbmi, umip, pku, ospke, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, la57, rdpid, overflow_recov, succor, fsrm, arch_capabilities
Ecpus
30.1
Scalability
100.33

System Resources and Accelerators

MEMORY
Memory Amount
42 GiB
Memory Amount Actual
44 GiB
GPU
GPU Count
1
GPU Memory Min
24 GiB
GPU Memory Total
24 GiB
GPU Manufacturer
NVIDIA
GPU Family
Ampere
GPU Model
A10
GPUs
  • NVIDIA Ampere NVIDIA A10 (Memory amount: 23028, Firmware version: 590.48.01, BIOS version: 94.02.5C.00.04, Clock rate: 1695)
STORAGE
Storage Size
400 GB
Storage Type
ssd
Storages
  • 400 GB ssd
NETWORK
Network Speed Baseline
8 Gbps
Network Speed Max
8 Gbps
Inbound Traffic
0 GB/month
Outbound Traffic
0 GB/month
IPv4
1

CPU and System Topology

Server Description

A dedicated AMD EPYC server with NVIDIA A10 acceleration, delivering strong database performance and optimized small-to-medium LLM inference.

GPU AcceleratedCompute OptimizedStorage & Database

OVHcloud a10-45 is a GPU-accelerated server featuring 30 dedicated AMD EPYC 9554 physical cores running at 3.3 GHz, 42.0 GB of RAM, a 400 GB local SSD, and a single NVIDIA A10 GPU with 24 GB of VRAM. Operating on the x86_64 architecture under a KVM hypervisor, this instance delivers strong CPU and database performance, with stress-ng and Passmark scores placing in the top 25%. The server excels in small-to-medium large language model inference, achieving top 10% speeds for 135M and 7B models. However, text generation for 70B models is a key tradeoff, falling into the bottom 10% due to VRAM limitations. With 8 Gbps network bandwidth and dedicated compute resources, the a10-45 is highly suited for GPU-accelerated workloads, software compilation, and database operations.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

1.82Score
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) 3,262,995 ops/sec 1,917,397 ops/sec 1.7 50.00% 50.00% +30.40%
Redis RPS (pipeline=16, SET) 32,019,252 ops/sec 11,681,410 ops/sec 2.74 20.00% 20.00% +22.30%
PassMark Memory Mark (composite) 2,897 2,418 1.2 10.00% 10.00% +1.84%
Memory bandwidth (read, 16 MB ~ L3) 267,350 MB/sec 108,140 MB/sec 2.47 10.00% 10.00% +9.46%
PassMark single-thread CPU 2,932 Mops/s 2,365 Mops/s 1.24 10.00% 10.00% +2.17%

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 2,029

Geekbench Multi-Core

Score: 14,616

Passmark CPU Scores

BENCHMARKSCORE
Mark
 60982
Compression
 800427
Encryption
 39850
Extended Instructions
 75798
Floating Point Maths
 161881
Integer Maths
 183632
Physics
 10281
Prime Numbers
 599
Single Threaded
 2932
String Sorting
 116494

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2897
Database Operations
 28598
Memory Latency
 71
Memory Read Cached
 27913
Memory Read Uncached
 26773
Memory Write
 25380

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
t2-le-45 1545 GiB1
l40s-90 1590 GiB1
a100-180 15180 GiB1
t1-le-90 1690 GiB2

Similar Servers

INSTANCEVENDORvCPUsMEMORYGPUs

a10-45 FAQs