.avif)
Powering the next generation of AI & high-performance computing.
Engineered for large-scale AI training, deep learning, and high-performance workloads, delivering unprecedented compute power and efficiency.
Why rent the L40 instead of buying?
Data center AI performance at a strong price point
The L40's Ada Lovelace architecture combines fourth-generation Tensor Cores with third-generation RT Cores — making it uniquely capable of both AI compute and professional rendering in a single GPU. It delivers 5× higher image generative AI inference performance versus the previous generation, making it a top choice for diffusion model pipelines, LLM fine-tuning, and visualization workloads.
Pay only for what you use
Purchasing an L40 costs upwards of $7,000–$10,000 per card. Runpod's on-demand pricing lets you access the same hardware with no capital commitment, no maintenance overhead, no depreciation.
Deploy in seconds, scale or switch when you're ready
Provision an L40 instance in seconds. Scale up for training runs, scale down for development, or switch to a higher-tier GPU without changing providers. Runpod handles the infrastructure so your team focuses on the work.
Use Cases
Popular use cases.
Designed for demanding workloads —learn if this GPU fits your needs.
Technical Specs
Ready for your most demanding workloads.
Essential technical specifications to help you choose the right GPU for your workload.
"The Runpod team has clearly prioritized the developer experience to create an elegant solution that enables individuals to rapidly develop custom AI apps or integrations while also paving the way for organizations to truly deliver on the promise of AI."
Amjad Masad
"Runpod is the only place I can deploy high-end GPU models instantly—no sales calls, no rate limits, no nonsense."
Daniel Chang
“The main value proposition for us was the flexibility Runpod offered. We were able to scale up effortlessly to meet the demand at launch.”
Josh Payne
“Runpod helped us scale the part of our platform that drives creation. That’s what fuels the rest—image generation, sharing, remixing. It starts with training.”
Matty Shimura
Comparison
Powerful GPUs. Globally available. Reliability you can trust.
30+ GPUs, 31 regions, instant scale. Fine-tune or go full Skynet—we’ve got you.
FAQs
Questions? Answers.
What are the current hourly rates for renting an L40 on Runpod?
Rates vary by availability. For the most current pricing, see the Runpod pricing page.
What's the difference between the L40 and L40S?
The L40 and L40S are distinct GPUs with different specs. The L40 has a 300W TDP and is optimized for mixed AI compute and professional graphics workloads. The L40S has a 350W TDP, higher AI tensor throughput, and is better suited to pure inference at scale. See the Runpod pricing page to compare current availability and rates for both.
Is the L40 good for generative AI workloads like image generation?
The L40 was specifically designed with image generative AI in mind, delivering 5× higher inference performance vs the previous generation. Its combination of fourth-generation Tensor Cores and third-generation RT Cores makes it particularly effective for Stable Diffusion, ControlNet, and similar pipelines.
Does the L40 support MIG or NVLink?
The L40 does not support Multi-Instance GPU (MIG) partitioning or NVLink. Multi-GPU communication is handled via PCIe. If MIG or high-bandwidth GPU-to-GPU interconnect is required for your workload, the A100 or H100 SXM are better fits.
When does renting an L40 make more sense than buying?
Renting is the better choice for project-based workloads, teams without capital for hardware, organizations scaling AI development, and anyone testing configurations before committing. Buying makes sense only with sustained, predictable full-utilization over a long horizon. For current rates to inform your decision, see the Runpod pricing page.
10,100,100,100
Requests since launch & 1M+ developers worldwide
