l40s-180 by OVHcloud

l40s-180 is a Cloud GPU (30 vCPUs, 180 GiB RAM, 400 GB NVMe, 2xL40S 48 GiB VRAM) server offered by OVHcloud with 30 vCPUs, 180 GiB of memory and 400 GB of storage. The pricing starts at 3.1282 USD per hour.
30 vCPU
180 GiB Memory
400 GB Storage
2 GPU
Spare SCore
89,986
(All-cores)
3,053
(Single-core)

Specifications

Server Metadata

Vendor ID
ovh
Name
l40s-180
Description
Cloud GPU (30 vCPUs, 180 GiB RAM, 400 GB NVMe, 2xL40S 48 GiB VRAM)
Family
Cloud GPU
Hw Virt
Status
active
Observed At
2026-10-31T19:15:36.094667

Availability

REGION / IDSPOTONDEMAND
GRA11 (FR) / GRA11
- 3.1282 USD/h

Processor

vCPUs
30
Hypervisor
KVM
CPU Allocation
Dedicated
CPU Cores
30
CPU Speed
2.75 GHz
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
9124
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
29.5
Scalability
98.33

System Resources and Accelerators

MEMORY
Memory Amount
180 GiB
Memory Amount Actual
176 GiB
ACCELERATORS
Accelerator Count
2
Accelerator Memory Min
48 GiB
Accelerator Memory Total
96 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Ada Lovelace
Accelerator Model
L40S
Accelerators
  • NVIDIA Ada Lovelace NVIDIA L40S (Memory amount: 46068, Firmware version: 590.48.01, BIOS version: 95.02.66.00.02, Clock rate: 2520)
  • NVIDIA Ada Lovelace NVIDIA L40S (Memory amount: 46068, Firmware version: 590.48.01, BIOS version: 95.02.66.00.02, Clock rate: 2520)
STORAGE
Storage Size
400 GB
Storage Type
nvme ssd
Storages
  • 400 GB nvme ssd
NETWORK
Network Speed Baseline
16 Gbps
Network Speed Max
16 Gbps
Inbound Traffic
0 GB/month
Outbound Traffic
0 GB/month
IPv4
1

CPU and System Topology

Server Description

A high-density GPU server featuring dual accelerators and dedicated AMD EPYC cores optimized for large language model inference and parallel computing.

GPU AcceleratedCompute OptimizedMemory Optimized

OVHcloud l40s-180 is a dedicated GPU-accelerated server designed for intensive parallel computing and machine learning workloads. Powered by an AMD EPYC 9124 processor with 30 physical cores and 30 vCPUs at 2.75 GHz, the system features 180 GB of RAM and a 400 GB NVMe SSD. Its primary acceleration is delivered by two NVIDIA L40S GPUs with a combined 96 GB of VRAM. Benchmark data highlights top-tier performance in LLM inference for prompt processing and text generation across 135M, 7B, and 70B models. Additionally, the server ranks in the top 25 percent for multi-core CPU stress tests, cryptographic operations, and database operations. With a 16 Gbps baseline network speed, this server is highly optimized for deep learning, large-scale AI inference, and high-performance computing tasks requiring dense GPU resources.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

1.4Score
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) 2,996,928 ops/sec 1,918,343 ops/sec 1.6 50.00% 50.00% +26.00%
Redis RPS (pipeline=16, SET) 28,191,853 ops/sec 11,704,734 ops/sec 2.3 20.00% 20.00% +18.00%
PassMark Memory Mark (composite) 2,713 2,416 1.1 10.00% 10.00% +0.96%
Memory bandwidth (read, 16 MB ~ L3) 59,349 MB/sec 108,466 MB/sec 0.54 10.00% 10.00% -6.00%
PassMark single-thread CPU 2,888 Mops/s 2,365 Mops/s 1.2 10.00% 10.00% +1.80%

GPU Bandwidth and Latency

Node (all GPUs)
Node baseline directional bandwidth
30.9 GB/s
Node GPU-to-host bandwidth
52.8 GB/s
Node host-to-GPU bandwidth
53.7 GB/s
Single GPU slot
Per-GPU GPU-to-host bandwidth
26.4 GB/s
Per-GPU host-to-GPU bandwidth
26.9 GB/s
Per-GPU host-device latency
763 ns
Benchmark Environment
Driver Version
 535.274.02
CUDA Version (driver)
 12.6
nvbandwidth Version
 v0.5
GPU Count
 2
P2P Supported
No
Efficiency
SM/CE copy efficiency
1.00

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 1,923

Geekbench Multi-Core

Score: 13,783

Passmark CPU Scores

BENCHMARKSCORE
Mark
 57,957
Compression
 773,241
Encryption
 38,392
Extended Instructions
 70,240
Floating Point Maths
 156,486
Integer Maths
 172,389
Physics
 6,759
Prime Numbers
 552
Single Threaded
 2,888
String Sorting
 109,379

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2,713
Database Operations
 22,676
Memory Latency
 79
Memory Read Cached
 27,687
Memory Read Uncached
 23,425
Memory Write
 21,703

Stress-ng Stressors

CPU integerSingleMultiScaling
atomic
 762.94 347.39 0.46×
bitops
 159,741 4,683,090 29.32×
branch
 213,287 6,220,242 29.16×
funccall
 615.54 18,103 29.41×
funcret
 20,845 616,876 29.59×
hash
 163,162 4,754,331 29.14×
intmath
 66,077 1,930,842 29.22×
nop
 626,113 18,275,817 29.19×
prime
 479,208 14,063,891 29.35×
rotate
 88,142 2,574,656 29.21×
str
 976,657 31,162,727 31.91×
wcs
 696,246 20,267,990 29.11×
CryptographySingleMultiScaling
crypt
 3,708 107,762 29.07×
CompressionSingleMultiScaling
jpeg
 888.8 23,142 26.04×
zlib
 49.99 1,711 34.23×
HypervisorSingleMultiScaling
clock
 25,598 164,265 6.42×
clone
 186.76 4,759 25.48×
context
 2,917 85,938 29.46×
cpu-sched
 63.68 1,941 30.47×
eventfd
 29,661 718,086 24.21×
fault
 9,910 110,788 11.18×
fork
 1,543 38,916 25.22×
getrandom
 53,062 1,524,763 28.74×
hrtimers
 142,785 2,823,073 19.77×
mprotect
 421,331 5,316,824 12.62×
mtx
 47,602,573 3,125,645,515 65.66×
munmap
 972.32 36,128 37.16×
null
 349,152 10,274,160 29.43×
pipe
 1,271,314 8,097,219 6.37×
priv-instr
 421,684 7,947,473 18.85×
resched
 5,872,994 5,270,543 0.90×
switch
 75,875 2,105,867 27.75×
timermix
 144,849 3,781,490 26.11×
tlb-shootdown
 9,222 109,565 11.88×
tsc
 782,118 22,870,297 29.24×
usersyscall
 316,941 7,114,493 22.45×
vdso
 83,544,125 2,448,776,536 29.31×
vfork
 11,720 108,691 9.27×
x86syscall
 3,982,678 116,647,257 29.29×
yield
 18,472,716 21,374,161 1.16×
zero
 2,748,346 80,650,798 29.35×
CPU float/SIMDSingleMultiScaling
eigen
 16,374 475,229 29.02×
expmath
 2,403 70,294 29.25×
fma
 918,426 26,946,882 29.34×
fp
 251.99 7,352 29.18×
fractal
 7.4 215.28 29.09×
hyperbolic
 3,800 110,935 29.19×
logmath
 4,554 133,853 29.39×
matrix
 4,916 144,006 29.29×
matrix-3d
 266.49 4,890 18.35×
monte-carlo
 171.42 4,854 28.31×
mpfr
 1,690 48,598 28.76×
powmath
 1,284 37,930 29.55×
trig
 1,869 54,740 29.30×
veccmp
 18,895 559,321 29.60×
vecfp
 1,802 52,641 29.21×
vecmath
 4,017 117,131 29.16×
vecshuf
 638.19 18,650 29.22×
vecwide
 28,591 833,784 29.16×
AlgorithmsSingleMultiScaling
bitonicsort
 10.4 305.19 29.35×
bsearch
 305.68 8,979 29.38×
bubblesort
 0.8 24.2 30.25×
fibsearch
 380.56 11,084 29.13×
heapsort
 10.8 273.59 25.33×
hsearch
 11,253 328,563 29.20×
insertionsort
 13 379.99 29.23×
malloc
 2,665,965 38,558,150 14.46×
mcontend
 53.08 3,785 71.31×
mergesort
 34 982.16 28.89×
qsort
 21.6 642.17 29.73×
skiplist
 7,014 205,087 29.24×
tree
 2 37.74 18.87×
MemorySingleMultiScaling
cache
 429,625 703,494 1.64×
cachehammer
 125,453 333,380 2.66×
cacheline
 29.98 1,177 39.26×
l1cache
 423.89 12,656 29.86×
memcpy
 442.81 13,113 29.61×
memrate
 3.14 9.45 3.01×
memthrash
 149.84 750.12 5.01×
ptr-chase
 15,252,468 225,157,954 14.76×
spinmem
 232.38 1,436 6.18×
stream
 199.69 29,982 150.14×
vm
 89,926 294,823 3.28×

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

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

l40s-180 FAQs