Rent NVIDIA L40S Cloud Instances
📊 Pricing at a Glance
NVIDIA L40S rental pricing ranges from $0.55/GPU/hr to $2.25/GPU/hr across 88 instances from 16 providers (updated June 2026).
Looking for a specific provider? See TensorDock NVIDIA L40S, Massed Compute NVIDIA L40S, or VERDA NVIDIA L40S.
Available Offers
Compare the top 5 cheapest offers from 16 providers.
| Provider | GPU Model | VRAM | Host Specs | Region | Price | Status | Action | |
|---|---|---|---|---|---|---|---|---|
 TensorDock | NVIDIA L40S 48GB VRAM | 48GB | 0 vCPU 0GB RAM | Wolverhampton | $0.55/GPU/hr | Available | ||
 Massed Compute | NVIDIA L40S 48GB VRAM | 48GB | 12 vCPU 72GB RAM 625GB Storage | Iowa | $0.88/GPU/hr | Available | ||
Massed Compute | NVIDIA L40S 48GB VRAM | 48GB | 12 vCPU 72GB RAM 625GB Storage | Iowa | $0.88/GPU/hr | Available | ||
 VERDA | NVIDIA L40S 48GB VRAM | 48GB | 20 vCPU 60GB RAM | Helsinki | $1.37/GPU/hr | Available | ||
 Ori | NVIDIA L40S 48GB VRAM | 48GB | 15 vCPU 90GB RAM 400GB Storage | Lille | $1.55/GPU/hr | Available |
QuantaCloud
Need GPUs at scale?
Building out an inference fleet or training cluster? QuantaCloud brokers reserved capacity across multiple data center partners. 16+ GPUs, flexible terms, custom quote in 24 hours.
Technical Specifications
Strengths & Limitations
- High memory capacity (48GB) ideal for large datasets and complex models.
- Excellent performance for both visualization and compute workloads.
- Supports NVIDIA virtual GPU (vGPU) software for improved resource utilization and management.
- Optimized for AI inference and training.
- Strong FP32 and Tensor Core performance.
- Higher power consumption compared to lower-end GPUs.
- May be overkill for less demanding tasks.
- Price point is higher than entry-level data center GPUs.
Top Use Cases
The L40S excels at accelerating AI inference workloads, enabling real-time insights and decision-making. Its Tensor Cores provide significant performance gains for deep learning models.
With its large memory capacity and powerful compute capabilities, the L40S is well-suited for data science tasks such as data analysis, model training, and simulation.
The L40S delivers exceptional performance for professional visualization applications, including CAD, CAE, and digital content creation. It supports high-resolution displays and complex 3D models.
Real-World Benchmark
Market Analysis
The NVIDIA L40S occupies a mid-range position in the data center GPU market, offering a compelling balance of performance and features for a variety of workloads. It competes with other GPUs in the same price range, such as the A30 ($0.22/hr), and offers a step up in performance from the L4 ($0.20/hr). Its large memory capacity makes it a strong contender for memory-intensive applications.
Frequently Asked Questions
What is the typical power consumption of the NVIDIA L40S?â–¾
The typical power consumption of the NVIDIA L40S is around 300W.
Does the NVIDIA L40S support NVIDIA vGPU?â–¾
Yes, the NVIDIA L40S supports NVIDIA vGPU software, allowing for virtualization and sharing of GPU resources across multiple virtual machines.
What type of workloads is the NVIDIA L40S best suited for?â–¾
The NVIDIA L40S is well-suited for a wide range of workloads, including AI inference, data science, professional visualization, and virtual workstations.
Alternative GPUs
Journalists, bloggers, and researchers: You're welcome to cite our data in your articles with attribution. Our pricing database is updated in real-time from 16+ cloud providers.