h200-1920-eph by OVHcloud
h200-1920-eph is a 224 vCPUs, 1920 GiB RAM, 20400 GB NVMe, 8xH200 141 GiB VRAM server offered by OVHcloud with 224 vCPUs, 1920 GiB of memory and 20.4 TB of storage.
224 vCPU
1920 GiB Memory
20.4 TB Storage
8 GPU
Spare SCore
470,348
(All-cores)
(All-cores)
3,673
(Single-core)
(Single-core)
Specifications
Server Metadata
Vendor ID | ovh |
Name | h200-1920-eph |
Description | 224 vCPUs, 1920 GiB RAM, 20400 GB NVMe, 8xH200 141 GiB VRAM |
Series | h200 |
Hw Virt | |
Average Time To Start | 246 |
Status | active |
Observed At | 2026-11-16T09:10:26.768697 |
Availability
| Region / ID | Spot | Ondemand |
|---|---|---|
EU-WEST-PAR (FR) / EU-WEST-PAR | - | 46.4184 USD/h |
Processor
vCPUs | 224 |
Hypervisor | KVM |
CPU Allocation | Dedicated |
CPU Cores | 224 |
CPU Speed | 3 GHz |
CPU Architecture | x86_64 |
CPU Manufacturer | AMD |
CPU Family | EPYC |
CPU Model | 9555 |
CPU L1D Cache | 64 KiB |
CPU L1D Cache Total | 14 MiB |
CPU L1I Cache | 64 KiB |
CPU L1I Cache Total | 14 MiB |
CPU L2 Cache | 512 KiB |
CPU L2 Cache Total | 112 MiB |
CPU L3 Cache | 16 MiB |
CPU L3 Cache Total | 4 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, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, avx_vnni, 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, movdiri, movdir64b, overflow_recov, succor, fsrm, avx512_vp2intersect, arch_capabilities |
Ecpus | 128.1 |
Scalability | 57.19 |
System Resources and Accelerators
| Memory | |
|---|---|
Memory Amount | 2 TB |
Memory Amount Actual | 2 TB |
| Accelerators | |
|---|---|
Accelerator Count | 8 |
Accelerator Memory Min | 141 GiB |
Accelerator Memory Total | 1 TB |
Accelerator Type | GPU |
Accelerator Manufacturer | NVIDIA |
Accelerator Family | Hopper |
Accelerator Model | H200 |
Accelerators |
|
| Storage | |
|---|---|
Storage Size | 20400 GB |
Storage Type | nvme ssd |
Storages |
|
Compatible Storage IDs | classic, high-speed, high-speed-gen2 |
| Network | |
|---|---|
Network Speed Baseline | 25 Gbps |
Network Speed Max | 25 Gbps |
Inbound Traffic | 0 GB/month |
Outbound Traffic | 0 GB/month |
IPv4 | 0 |
CPU and System Topology
Economics
Performance
GPU Bandwidth and Latency
| Node (all GPUs) | |
|---|---|
Node baseline directional bandwidth | 145.5 GB/s |
Node GPU-to-host bandwidth | 225.6 GB/s |
Node host-to-GPU bandwidth | 224.5 GB/s |
| Peer-to-peer | |
|---|---|
GPU-to-GPU P2P duplex bandwidth | 132.6 GB/s |
GPU-to-GPU P2P gather bandwidth | 399.6 GB/s |
GPU-to-GPU P2P latency | 589 ns |
GPU-to-GPU P2P bandwidth | 133.2 GB/s |
| Single GPU slot | |
|---|---|
Per-GPU GPU-to-host bandwidth | 56.2 GB/s |
Per-GPU host-to-GPU bandwidth | 56.8 GB/s |
Per-GPU host-device latency | 1,094 ns |
Per-GPU device memory copy bandwidth | 2007.5 GB/s |
| Benchmark Environment | |
|---|---|
Driver Version | 595.99.02 |
CUDA Version (driver) | 13.2 |
nvbandwidth Version | v0.8 |
GPU Count | 8 |
P2P Supported | Yes |
| Efficiency | |
|---|---|
SM/CE copy efficiency | 0.92 |
Memory Bandwidth
Compression
OpenSSL
Stress-ng Stressors
| CPU integer | Single | Multi | Scaling |
|---|---|---|---|
atomic | 490.71 | 248.78 | 0.51× |
bitops | 226,016 | 30,972,825 | 137.04× |
branch | 169,936 | 33,722,309 | 198.44× |
funccall | 887.34 | 129,753 | 146.23× |
funcret | 27,283 | 4,047,630 | 148.36× |
hash | 213,852 | 37,730,163 | 176.43× |
intmath | 78,303 | 11,457,764 | 146.33× |
nop | 422,203 | 61,561,003 | 145.81× |
prime | 609,768 | 88,204,066 | 144.65× |
rotate | 139,876 | 17,978,878 | 128.53× |
str | 1,487,034 | 189,636,104 | 127.53× |
wcs | 1,023,942 | 118,726,946 | 115.95× |
| Cryptography | Single | Multi | Scaling |
|---|---|---|---|
crypt | 5,260 | 669,026 | 127.19× |
| Compression | Single | Multi | Scaling |
|---|---|---|---|
jpeg | 1,236 | 38,517 | 31.16× |
zlib | 58.62 | 13,997 | 238.78× |
| Hypervisor | Single | Multi | Scaling |
|---|---|---|---|
clock | 46,964 | 119,678 | 2.55× |
clone | 288.3 | 10,684 | 37.06× |
context | 8,328 | 1,592,894 | 191.27× |
cpu-sched | 59.98 | 13,191 | 219.92× |
eventfd | 69,016 | 6,116,196 | 88.62× |
fault | 37,958 | 106,558 | 2.81× |
fork | 3,856 | 34,467 | 8.94× |
getrandom | 96,627 | 12,407,655 | 128.41× |
hrtimers | 145,156 | 13,452,820 | 92.68× |
mprotect | 462,243 | 34,399,955 | 74.42× |
mtx | 38,606,654 | 12,809,413,141 | 331.79× |
munmap | 3,459 | 34,554 | 9.99× |
null | 1,391,174 | 178,771,628 | 128.50× |
pipe | 865,590 | 58,367,969 | 67.43× |
priv-instr | 1,369,033 | 30,597,697 | 22.35× |
resched | 7,876,091 | 101,549,147 | 12.89× |
switch | 245,865 | 33,862,150 | 137.73× |
timermix | 309,548 | 45,595,041 | 147.30× |
tlb-shootdown | 16,713 | 288,304 | 17.25× |
tsc | 867,637 | 191,356,108 | 220.55× |
usersyscall | 1,069,425 | 29,765,932 | 27.83× |
vdso | 96,067,635 | 18,212,988,876 | 189.59× |
vfork | 22,800 | 93,069 | 4.08× |
x86syscall | 18,357,253 | 3,332,028,430 | 181.51× |
yield | 226,114,101 | 287,214,850 | 1.27× |
zero | 10,878,209 | 1,606,752,770 | 147.70× |
| CPU float/SIMD | Single | Multi | Scaling |
|---|---|---|---|
eigen | 17,149 | 2,381,591 | 138.88× |
expmath | 3,947 | 607,543 | 153.94× |
fma | 1,540,928 | 232,336,908 | 150.78× |
fp | 201.6 | 35,126 | 174.23× |
fractal | 8.8 | 1,462 | 166.15× |
hyperbolic | 5,390 | 917,421 | 170.20× |
logmath | 5,545 | 969,019 | 174.76× |
matrix | 9,144 | 873,171 | 95.50× |
matrix-3d | 1,511 | 6,635 | 4.39× |
monte-carlo | 451.9 | 73,998 | 163.75× |
mpfr | 2,370 | 337,483 | 142.37× |
powmath | 1,821 | 319,828 | 175.67× |
trig | 2,399 | 387,187 | 161.40× |
veccmp | 29,745 | 4,171,347 | 140.24× |
vecfp | 2,362 | 409,647 | 173.40× |
vecmath | 4,580 | 814,480 | 177.85× |
vecshuf | 989.07 | 133,585 | 135.06× |
vecwide | 39,684 | 5,328,743 | 134.28× |
| Algorithms | Single | Multi | Scaling |
|---|---|---|---|
bitonicsort | 12.6 | 1,621 | 128.66× |
bsearch | 344.66 | 53,279 | 154.58× |
bubblesort | 1.2 | 149.8 | 124.83× |
fibsearch | 421.51 | 67,024 | 159.01× |
heapsort | 14.2 | 1,986 | 139.86× |
hsearch | 13,348 | 1,589,998 | 119.12× |
insertionsort | 15.8 | 1,357 | 85.90× |
malloc | 4,968,894 | 252,674,565 | 50.85× |
mcontend | 68.63 | 30,311 | 441.65× |
mergesort | 38.6 | 5,980 | 154.92× |
qsort | 26.4 | 3,845 | 145.66× |
skiplist | 8,333 | 1,394,674 | 167.36× |
tree | 2.6 | 149.43 | 57.47× |
| Memory | Single | Multi | Scaling |
|---|---|---|---|
cache | 1,109,241 | 1,607,932 | 1.45× |
cachehammer | 277,727 | 15,119,323 | 54.44× |
cacheline | 78.95 | 4,033 | 51.08× |
l1cache | 667.82 | 49,161 | 73.61× |
memcpy | 804.02 | 91,120 | 113.33× |
memrate | 0.99 | 34.67 | 35.02× |
memthrash | 473.7 | 814.09 | 1.72× |
ptr-chase | 75,480,127 | 937,034,014 | 12.41× |
spinmem | 351.99 | 17,886 | 50.81× |
stream | 285.9 | 314,796 | 1101.07× |
vm | 229,188 | 310,564 | 1.36× |
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
| INSTANCE | vCPUs | MEMORY | Accelerators |
|---|
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | Accelerators |
|---|