a10-180 is a Cloud GPU (120 vCPUs, 170 GiB RAM, 400 GB SSD, 4xA10 24 GiB VRAM) server offered by OVHcloud with 120 vCPUs, 170 GiB of memory and 400 GB of storage.
120 vCPU
170 GiB Memory
400 GB Storage
4 GPU
Spare SCore
199,581
(All-cores)
(All-cores)
3,108
(Single-core)
(Single-core)
Specifications
Server Metadata
Vendor ID | ovh |
Name | a10-180 |
Description | Cloud GPU (120 vCPUs, 170 GiB RAM, 400 GB SSD, 4xA10 24 GiB VRAM) |
Family | Cloud GPU |
Hw Virt | |
Status | active |
Observed At | 2026-10-31T15:51:51.805806 |
Availability
| REGION / ID | SPOT | ONDEMAND |
|---|---|---|
GRA11 (FR) / GRA11 | - | 3.3963 USD/h |
GRA9 (FR) / GRA9 | - | 3.3963 USD/h |
Processor
vCPUs | 120 |
Hypervisor | KVM |
CPU Allocation | Dedicated |
CPU Cores | 120 |
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 | 8 MiB |
CPU L1I Cache | 64 KiB |
CPU L1I Cache Total | 8 MiB |
CPU L2 Cache | 512 KiB |
CPU L2 Cache Total | 60 MiB |
CPU L3 Cache | 16 MiB |
CPU L3 Cache Total | 2 GiB |
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 | 64.2 |
Scalability | 53.5 |
System Resources and Accelerators
| MEMORY | |
|---|---|
Memory Amount | 170 GiB |
Memory Amount Actual | 176 GiB |
| ACCELERATORS | |
|---|---|
Accelerator Count | 4 |
Accelerator Memory Min | 24 GiB |
Accelerator Memory Total | 96 GiB |
Accelerator Type | GPU |
Accelerator Manufacturer | NVIDIA |
Accelerator Family | Ampere |
Accelerator Model | A10 |
Accelerators |
|
| STORAGE | |
|---|---|
Storage Size | 400 GB |
Storage Type | ssd |
Storages |
|
| NETWORK | |
|---|---|
Network Speed Baseline | 25 Gbps |
Network Speed Max | 25 Gbps |
Inbound Traffic | 0 GB/month |
Outbound Traffic | 0 GB/month |
IPv4 | 1 |
Server Description
A high-density GPU instance featuring four accelerators and 120 dedicated cores for parallel computing and machine learning inference.
GPU AcceleratedCompute Optimized
The OVHcloud a10-180 is a GPU-accelerated server featuring an AMD EPYC 9554 processor with 120 dedicated physical cores running at 3.3 GHz on the x86_64 architecture. It is equipped with 170.0 GB of system memory, four NVIDIA Ampere A10 GPUs providing 96 GB of total VRAM, a 400 GB local SSD, and a 25 Gbps baseline network bandwidth. Benchmark data indicates top-tier multi-core CPU performance, with strong results in cryptographic operations, software compilation, and multi-threaded decompression. The server excels in LLM inference, delivering high token-generation speeds across various model sizes. However, the memory-to-core ratio is low at 1.42 GB per core, and local storage is limited. This configuration is suited for machine learning inference, parallel compute workloads, and ray tracing applications.
Economics
Performance
GPU Bandwidth and Latency
| Node (all GPUs) | |
|---|---|
Node baseline directional bandwidth | 44.2 GB/s |
Node GPU-to-host bandwidth | 52.9 GB/s |
Node host-to-GPU bandwidth | 53.5 GB/s |
| Single GPU slot | |
|---|---|
Per-GPU GPU-to-host bandwidth | 13.2 GB/s |
Per-GPU host-to-GPU bandwidth | 13.4 GB/s |
Per-GPU host-device latency | 688 ns |
| Benchmark Environment | |
|---|---|
Driver Version | 535.274.02 |
CUDA Version (driver) | 12.6 |
nvbandwidth Version | v0.5 |
GPU Count | 4 |
P2P Supported | No |
| Efficiency | |
|---|---|
SM/CE copy efficiency | 1.00 |
Compression
OpenSSL
Geekbench Single-Core
Score: 2,023
Geekbench Multi-Core
Score: 15,749
Passmark CPU Scores
| BENCHMARK | SCORE |
|---|---|
Mark | 99,328 |
Compression | 2,126,854 |
Encryption | 140,722 |
Extended Instructions | 136,045 |
Floating Point Maths | 340,165 |
Integer Maths | 587,807 |
Physics | 7,511 |
Prime Numbers | 964 |
Single Threaded | 2,926 |
String Sorting | 165,310 |
Passmark Memory Scores
| BENCHMARK | SCORE |
|---|---|
Memory Mark | 3,092 |
Database Operations | 29,006 |
Memory Latency | 68 |
Memory Read Cached | 27,940 |
Memory Read Uncached | 27,094 |
Memory Write | 25,747 |
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
| INSTANCE | vCPUs | MEMORY | Accelerators |
|---|---|---|---|
| rtx5000-28 | 4 | 28 GiB | 1 |
| t1-le-45 | 8 | 45 GiB | 1 |
| rtx5000-56 | 8 | 56 GiB | 2 |
| t2-le-45 | 15 | 45 GiB | 1 |
| l40s-90 | 15 | 90 GiB | 1 |
| a100-180 | 15 | 180 GiB | 1 |
| t1-le-90 | 16 | 90 GiB | 2 |
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | Accelerators |
|---|