NVIDIA L40S cloud GPU rental

The NVIDIA L40S is a datacenter Ada Lovelace GPU with 48 GB of GDDR6 at 864 GB/s of memory bandwidth. On FastInfra it is a good fit for 30B–70B inference, full fine-tuning of mid-size models, video generation. As a rule of thumb, one L40S holds the weights of a model of about 19B parameters at 16-bit precision, or about 76B with 4-bit quantization, after leaving room for the KV cache.

Two on-demand tiers are available. Secure runs in vetted datacenters at $1.18 per GPU-hour; Value uses lower-cost community hosts at $0.854 per GPU-hour for the same GPU model, with more variable capacity.

Best for

30B–70B inference, full fine-tuning of mid-size models, video generation.

About the Ada Lovelace architecture

Ada Lovelace GPUs have fourth-generation Tensor Cores with FP8 support and large L2 caches. They are a cost-efficient choice for inference, Stable Diffusion and ComfyUI, video generation, rendering and LoRA fine-tuning, where memory capacity matters more than the multi-GPU interconnect of datacenter parts.

Only need inference?

If you want to call an open model such as Llama, Qwen, DeepSeek or GPT-OSS rather than manage a server, the pay-per-token inference API is often cheaper than keeping a GPU busy around the clock. It is OpenAI-compatible and uses the same account and wallet as your pods. Browse every model with live prices.

How much does it cost to rent an NVIDIA L40S per hour?

$1.18 per GPU-hour on the Secure tier and $0.854 on the Value tier. Billing is per minute while the pod exists, so 24/7 use for a 730-hour month costs about $623 per GPU at the lowest on-demand rate. Prices sync from live capacity and are shown before you deploy.

How much VRAM does the NVIDIA L40S have?

48 GB of GDDR6 at 864 GB/s of memory bandwidth. The chip is rated at up to 350 W. A pod with 8 GPUs gives 384 GB of combined VRAM for tensor- or pipeline-parallel workloads.

What size LLM can I run on an NVIDIA L40S?

Roughly 19B parameters at FP16 or BF16, 38B at 8-bit and 76B at 4-bit on a single GPU, reserving about 20% of VRAM for the KV cache and activations. Mixture-of-experts models need memory for all experts, not only the active ones. Long contexts and large batches need more headroom.

Is the NVIDIA L40S billed per hour or per minute?

Per minute. The hourly rate is divided by 60 and charged for every minute the pod exists. Attached volumes bill per GB-month and continue while a pod is stopped; delete the pod to stop all charges. There is no minimum term or reservation fee.

How do I rent an NVIDIA L40S on FastInfra?

Create an account, add prepaid credit, open the GPU configurator and choose the L40S, the tier, the GPU count, a container template and storage. The configurator shows the hourly and monthly price, then deploys a pod you reach over SSH or JupyterLab within minutes.

Can I rent multiple L40S GPUs in one pod?

Yes, up to 8 per pod. The price scales linearly: 8 GPUs cost $9.42 per hour on Secure.

Is there a cheaper GPU than the L40S with the same VRAM?

Yes. The NVIDIA RTX A6000 has 48 GB and starts at $0.357 per hour. It differs in architecture (Ampere), memory bandwidth and multi-GPU interconnect, so compare throughput for your workload before switching.