NVIDIA · Ada Lovelace

Rent L40S

NVIDIA L40S GPU, 48 GB.LLM inferenceRenderingVirtual desktops

Full price from

—

in stock, per GPU-hour

Spot from

—

in stock, per GPU-hour

Offers in stock

0 of 19

full price or spot

Providers in stock

0 of 5

full price or spot

Offers (20)

GcoreNo stock dataSelf-service, ready in 15–40 minNot linked · PCIe only

8× L40S48 GB each, 384 GB total

United States · 2048 GB RAM · 2x960gb NVMe, 4x7.68TB NVMe RI SSD | 8xNvidia L40s

Details

Stock and price checked 14 min ago.

You start it yourself once there is stock.

This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.

bm3-infrastructure-ai-large-l40s-48-8

Full price

€10.18

per hour, whole instance, 8 GPUs

€1.27/h per GPU

View offer

GcoreNo stock dataSelf-service, ready in 15–40 minNot linked · PCIe only

8× L40S48 GB each, 384 GB total

Luxembourg · 2048 GB RAM · 2x960gb NVMe, 4x7.68TB NVMe RI SSD | 8xNvidia L40s

Details

Stock and price checked 14 min ago.

You start it yourself once there is stock.

This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.

bm3-infrastructure-ai-large-l40s-48-8

Full price

€10.18

per hour, whole instance, 8 GPUs

€1.27/h per GPU

View offer

OVHcloudNo stock dataSelf-service

1× L40S48 GB VRAM

France · 15 vCPU · 90 GB RAM · 8 Gbit/s · 400GB NVMe

Details

Stock and price checked 14 min ago.

You start it yourself once there is stock.

l40s-90

Full price

€1.40

per hour, whole instance, 1 GPU

View offer

OVHcloudNo stock dataSelf-serviceNot linked · PCIe only

2× L40S48 GB each, 96 GB total

France · 30 vCPU · 180 GB RAM · 16 Gbit/s · 400GB NVMe

Details

Stock and price checked 14 min ago.

You start it yourself once there is stock.

This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.

l40s-180

Full price

€2.80

per hour, whole instance, 2 GPUs

€1.40/h per GPU

View offer

OVHcloudNo stock dataSelf-serviceNot linked · PCIe only

4× L40S48 GB each, 192 GB total

France · 60 vCPU · 360 GB RAM · 25 Gbit/s · 400GB NVMe

Details

Stock and price checked 14 min ago.

You start it yourself once there is stock.

This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.

l40s-360

Full price

€5.60

per hour, whole instance, 4 GPUs

€1.40/h per GPU

View offer

ScalewayNo stock data

1× L40S48 GB VRAM

France · 8 vCPU · 96 GB RAM · 2.5 Gbit/s · Block, Scratch

Details

Stock and price checked 14 min ago.

L40S-1-48G

Full price

€1.47

per hour, whole instance, 1 GPU

View offer

ScalewayNo stock data

1× L40S48 GB VRAM

Poland · 8 vCPU · 96 GB RAM · 2.5 Gbit/s · Block, Scratch

Details

Stock and price checked 14 min ago.

L40S-1-48G

Full price

€1.47

per hour, whole instance, 1 GPU

View offer

ScalewayNo stock dataNot linked · PCIe only

2× L40S48 GB each, 96 GB total

France · 16 vCPU · 192 GB RAM · 5 Gbit/s · Block, Scratch

Details

Stock and price checked 14 min ago.

This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.

L40S-2-48G

Full price

€2.94

per hour, whole instance, 2 GPUs

€1.47/h per GPU

View offer

Provider not namedMight be available

L40S

EU · 17 offers

Full price

from €1.04

per GPU, per hour

Spot from €0.78

See all 19 offers

Price and availability history

Price per GPU-hour

Excluding VAT.

Providers with stock

Each provider counts once. Full price and spot are separate.

Not enough history in this range yet. We record every 10 minutes since 9 November 2026.

Share of offers in stock

Full price. Offers we can't say are really sold there are left out until they've been in stock once.

Not enough history in this range yet. We record every 10 minutes since 9 November 2026.

Units free

No provider reports a number for this GPU.

Not enough history in this range yet. We record every 10 minutes since 9 November 2026.

Stock by provider

In stock, yes or no, for every provider selling this GPU. A filled band means in stock: green at full price, orange as spot.

Not enough history in this range yet. We record every 10 minutes since 9 November 2026.

Using several together

Can't be linked. This GPU has no NVLink, so several in one server only talk over PCIe at up to 64 GB/s. Each card keeps its own 48 GB. That suits running a separate job on each card. Splitting one model across them works, but slowly.

Specifications

No NVLink; host link PCIe Gen4 x16 64 GB/s.

Memory

VRAM: 48 GB
Memory type: GDDR6
Memory bandwidth How fast the GPU reaches its memory. Often limits LLM speed: 864 GB/s
ECC memory Detects and corrects memory errors: Yes

Compute

FP32 Speed at 32-bit precision: 91.6 TFLOPS
FP16 Speed at 16-bit precision: 733 TFLOPS
BF16 16-bit AI format. Standard for training and full-quality inference: 733 TFLOPS
FP8 8-bit AI format. About half the memory of BF16, slightly lower quality: 1,466 TFLOPS
INT8 8-bit integer speed, used by quantized models: 1,466 TOPS
FP8 support: Yes
FP4 support: No
Transformer Engine Hardware that speeds up FP8 and FP4: Yes
Compute cores: 18,176

Multi-GPU and connectivity

NVSwitch Lets every GPU in a server talk to every other at full speed: No
PCIe generation: 4
PCIe lanes: 16
PCIe bandwidth: 64 GB/s

Sharing and security

MIG partitioning Splits one GPU into several isolated smaller GPUs: No
Max MIG instances: 0
vGPU: Yes
Confidential computing: No

Hardware

Architecture: Ada Lovelace
Launch year: 2023
Process node: TSMC 4N
Power (TDP) Maximum power draw: 350 W
Cooling: passive

Video

NVENC engines: 3
NVDEC engines: 3
AV1 encode: Yes
AV1 decode: Yes

Sources (37)