48GB GDDR6 with Ada Lovelace FP8 support. Strong inference throughput at a lower cost than A100 or H100 . AV1 hardware encoding makes it versatile for media and AI workloads.

When is the L40S not a good fit?

PCIe-only with no NVLink, limiting multi-GPU training performance. GDDR6 memory bandwidth (864 GB/s) is significantly lower than HBM-based data center GPUs.

Are L40S prices going up or down?

On-demand pricing has decreased by about 13% since June 2025, dropping from $1.97 to $1.71/hr per GPU.

What size AI models can the L40S run?

With 48GB of VRAM, the L40S can typically run models up to about 30B parameters in FP16, or 70B-class models in 4-bit quantized form for inference.

How much VRAM does the L40S have?

The L40S has 48GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.

What is the L40S's memory bandwidth?

The L40S has 864 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.

What data types does the L40S support?

The L40S supports 6 precision formats. Training: BF16, FP16, TF32, FP32. Inference: FP8, INT8.

Does the L40S support NVLink?

No. The L40S is a PCIe-only GPU with no NVLink, so it is better suited to single-GPU inference and smaller-scale workloads than large distributed training jobs.

How much does the L40S cost per hour?

L40S pricing currently ranges from $0.50/hr to $7.58/hr per GPU, depending on the provider, instance type, and billing model.

How much does the L40S cost per month?

At 720 hours per month, one L40S can cost between $360.00 to $5,455.58 per month, depending on the provider. Reserved and spot pricing can lower that further.

Which cloud providers offer the L40S?

The L40S is available from 28 cloud providers, including Amazon Web Services, Civo, Runpod. Pricing and availability vary by region and billing model.

Can I rent the L40S in the cloud?

Yes. We currently track 134 L40S listings across 28 cloud providers: Billing type Listings Avg $/GPU/hr On-demand 78 $1.70/hr Reserved 52 $1.34/hr Spot 4 $0.78/hr

Nvidia L40S

Cost-effective data center GPU for AI inference and media workloads.

Compare vs other GPUs →

Aggregating historical prices...

Key Specifications

Architecture

Ada Lovelace

Memory

48GB GDDR6

Memory Bandwidth

864 GB/s

Release date

Q3 2023

Compare Cloud Provider Prices

Listings for the L40S reach $7.58/hr, often reflecting a premium for high availability. However, you might be able to find available instances from as low as $0.50/hr per GPU (spot instance).

Billing

Max price/hr

Min GPUs

Min vCPUs

Min RAM (GB)

of shown

Default ranking

Our algorithm weighs five factors to find the most relevant matches for you:

Price: We blend total hourly price with price-per-GPU to balance affordability and value.
Specs: We favor offers with higher CPU, RAM, and GPU Memory.
Billing: We favor on-demand billing for simplicity and flexibility over spot instances, reservations, and custom quotes.
Location: We blend both datacenter proximity and provider HQ location. Datacenter location matters for latency, while HQ location matters for compliance and support.
Provider diversity: Each time a provider appears in the list, their subsequent offerings are ranked a little lower, so one provider's offerings don't crowd out the top positions.

Sorting and filtering

Click any column header to sort by that column. Use the filters above the table to narrow results by billing type, GPU count, vCPUs, or RAM. Custom sorting resets the default relevance ranking.

Transparency and funding

Ads and sponsors: Any paid placements are fixed at the top and clearly labeled as sponsored content.

Affiliates: Any affiliate links will be indicated to you as well. We may earn a commission if you click them, but this never influences the ranking order.

Provider	GPUs	Total VRAM	vCPUs	RAM	Billing	$/GPU/h	Total/h	Availability
Runpod Our sponsor	1x L40S 1x L40S 48GB (secure-cloud)	48GB	9	50GB	Reserved (12mo) Reserved capacity with a 1-year minimum commitment.	$0.70	$0.70	Available	View
Novita	1x L40S 1x L40S 48GB	48GB	--	--	On-Demand Pay-as-you-go pricing. No term commitments.	$0.55	$0.55	Unknown	View
Runpod	1x L40S 1x L40S 48GB (community-cloud)	48GB	9	50GB	On-Demand Pay-as-you-go pricing. No term commitments.	$0.79	$0.79	Available	View
Packet·ai	1x L40S 1x L40S 48GB	48GB	--	--	On-Demand Pay-as-you-go pricing. No term commitments.	$0.92	$0.92	Unknown	View
Crusoe	1x L40S 1x L40S 48GB (l40s-48gb.1x)	48GB	8	147GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.00	$1.00	Unknown	View
Fly.io	1x L40S 1x L40S 48GB	48GB	--	--	On-Demand Pay-as-you-go pricing. No term commitments.	$1.25	$1.25	Unknown	View
DigitalOcean	1x L40S 1x L40S 48GB	48GB	8	64GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.57	$1.57	Unknown	View
Vultr	1x L40S 1x L40S 48GB	48GB	16	180GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.67	$1.67	Unknown	View
AWS	1x L40S 1x L40S 48GB (g6e.xlarge)	48GB	4	32GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.86	$1.86	Available	View
Together	1x L40S 1x L40S 48GB	48GB	--	--	On-Demand Pay-as-you-go pricing. No term commitments.	$2.10	$2.10	Unknown	View
Runpod	1x L40S 1x L40S 48GB (secure-cloud)	48GB	9	50GB	On-Demand Pay-as-you-go pricing. No term commitments.	$0.86	$0.86	Available	View
Sesterce	1x L40S 1x L40S 48GB	48GB	22	128GB	On-Demand Pay-as-you-go pricing. No term commitments.	$0.97	$0.97	Available	View
Koyeb	1x L40S 1x L40S 48GB (L40S)	48GB	15	64GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.20	$1.20	Unknown	View
Civo	1x L40S 1x L40S 48GB	48GB	12	96GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.29	$1.29	Unknown	View
UpCloud	1x L40S 1x L40S 48GB	48GB	8	64GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.29	$1.29	Unknown	View
Nebius	1x L40S PCIe 1x L40S 48GB PCIe	48GB	8	32GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.55	$1.55	Available	View
OVH	1x L40S 1x L40S 48GB (l40s-90)	48GB	15	90GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.80	$1.80	Unknown	View
AWS	1x L40S 1x L40S 48GB (g6e.2xlarge)	48GB	8	64GB	On-Demand Pay-as-you-go pricing. No term commitments.	$2.24	$2.24	Available	View
Novita	8x L40S 8x L40S 48GB	384GB	--	--	On-Demand Pay-as-you-go pricing. No term commitments.	$0.55	$4.40	Unknown	View
Vultr	2x L40S 2x L40S 48GB	96GB	32	375GB	On-Demand Pay-as-you-go pricing. No term commitments.	$1.67	$3.34	Unknown	View
No offerings matching your filters.

Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.

Frequently Asked Questions

Why choose the L40S?: 48GB GDDR6 with Ada Lovelace FP8 support. Strong inference throughput at a lower cost than A100 or H100. AV1 hardware encoding makes it versatile for media and AI workloads.
When is the L40S not a good fit?: PCIe-only with no NVLink, limiting multi-GPU training performance. GDDR6 memory bandwidth (864 GB/s) is significantly lower than HBM-based data center GPUs.
Are L40S prices going up or down?: On-demand pricing has decreased by about 13% since June 2025, dropping from $1.97 to $1.71/hr per GPU.
What size AI models can the L40S run?: With 48GB of VRAM, the L40S can typically run models up to about 30B parameters in FP16, or 70B-class models in 4-bit quantized form for inference.
How much VRAM does the L40S have?: The L40S has 48GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.
What is the L40S's memory bandwidth?: The L40S has 864 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.
What data types does the L40S support?: The L40S supports 6 precision formats. Training: BF16, FP16, TF32, FP32. Inference: FP8, INT8.
Does the L40S support NVLink?: No. The L40S is a PCIe-only GPU with no NVLink, so it is better suited to single-GPU inference and smaller-scale workloads than large distributed training jobs.
How much does the L40S cost per hour?: L40S pricing currently ranges from $0.50/hr to $7.58/hr per GPU, depending on the provider, instance type, and billing model.
How much does the L40S cost per month?: At 720 hours per month, one L40S can cost between $360.00 to $5,455.58 per month, depending on the provider. Reserved and spot pricing can lower that further.
Which cloud providers offer the L40S?: The L40S is available from 28 cloud providers, including Amazon Web Services, Civo, Runpod. Pricing and availability vary by region and billing model.
Can I rent the L40S in the cloud?: Yes. We currently track 134 L40S listings across 28 cloud providers:

Billing type Listings Avg $/GPU/hr

On-demand 78 $1.70/hr

Reserved 52 $1.34/hr

Spot 4 $0.78/hr

Billing type	Listings	Avg $/GPU/hr
On-demand	78	$1.70/hr
Reserved	52	$1.34/hr
Spot	4	$0.78/hr

Technical Specifications


GPU Architecture	NVIDIA Ada Lovelace Architecture
GPU Memory	48GB GDDR6
Memory Bandwidth	864GB/s
Interconnect Interface	PCIe Gen4 x16: 64GB/s bidirectional
NVIDIA Ada Lovelace Architecture-Based CUDA® Cores	18,176
NVIDIA Third-Generation RT Cores	142
NVIDIA Fourth-Generation Tensor Cores	568
RT Core Performance TFLOPS	209
FP32 TFLOPS	91.6
TF32 Tensor Core TFLOPS	183
BFLOAT16 Tensor Core TFLOPS	362.05
FP16 Tensor Core	362.05
FP8 Tensor Core	733
Peak INT8 Tensor TOPS	733
Peak INT4 Tensor TOPS	733
Form Factor	4.4" (H) x 10.5" (L), dual slot
Display Ports	4x DisplayPort 1.4a
Max Power Consumption	350W
Power Connector	16-pin
Thermal	Passive
Virtual GPU (vGPU) Software Support	Yes
vGPU Profiles Supported	See the virtual GPU licensing guide
NVENC, NVDEC	3x, 3x (includes AV1 encode and decode)
Secure Boot With Root of Trust	Yes
NEBS Ready	Level 3
MIG Support	No
NVIDIA® NVLink® Support	No