NVIDIA L4 cloud GPU rental
Rent an NVIDIA L4 cloud GPU from $0.638 per hour with 24 GB of GDDR6 at 300 GB/s of memory bandwidth. FastInfra bills pods per minute with no commitment, so a one-hour experiment costs $0.638 and you stop paying the moment you delete the pod. Run 1 to 9 GPUs per pod, connect over SSH or JupyterLab, and see the exact price before you deploy.
Prices synced November 3, 2026 · billed per minute
L4 specs and pricing
The NVIDIA L4 is a datacenter Ada Lovelace GPU with 24 GB of GDDR6 at 300 GB/s of memory bandwidth. On FastInfra it is a good fit for 7B–13B inference, LoRA fine-tuning, ComfyUI and Stable Diffusion. As a rule of thumb, one L4 holds the weights of a model of about 9.5B parameters at 16-bit precision, or about 38B with 4-bit quantization, after leaving room for the KV cache.
The L4 runs on the Secure tier in vetted datacenters at $0.638 per GPU-hour.
L4 price per hour by GPU count
Live FastInfra prices per pod-hour. Pods bill per minute, so you pay only for the minutes a pod exists.
| Pod size | Total VRAM | Secure / hr | Month (730 h, lowest) |
|---|---|---|---|
| 1× L4 | 24 GB | $0.638 | $466 |
| 2× L4 | 48 GB | $1.28 | $931 |
| 4× L4 | 96 GB | $2.55 | $1,863 |
| 8× L4 | 192 GB | $5.10 | $3,726 |
What an L4 costs over time
One GPU at the lowest on-demand rate ($0.638/hr).
| Duration | On-demand |
|---|---|
| 1 hour | $0.638 |
| 8-hour working day | $5.10 |
| 24 hours | $15.31 |
| 1 week (168 hours) | $107 |
| 1 month (730 hours) | $466 |
Which LLMs fit on the L4?
GPUs needed to hold the model weights with about 20% of VRAM left for the KV cache. Rule of thumb only: long contexts and big batches need more.
| Model size | Examples | FP16 / BF16 | 8-bit | 4-bit |
|---|---|---|---|---|
| 7–8B | Llama 3.1 8B, Qwen3 8B, Mistral 7B | 1 GPU | 1 GPU | 1 GPU |
| 12–14B | Gemma 3 12B, Qwen3 14B, Phi-4 | 2 GPUs | 1 GPU | 1 GPU |
| 27–32B | Gemma 3 27B, Qwen3 32B | 4 GPUs | 2 GPUs | 1 GPU |
| 70B | Llama 3.3 70B | 8 GPUs | 4 GPUs | 2 GPUs |
| 120B | GPT-OSS 120B | Needs more GPUs | 8 GPUs | 4 GPUs |
| 235B | Qwen3 235B-A22B | Needs more GPUs | Needs more GPUs | 8 GPUs |
| 405B | Llama 3.1 405B | Needs more GPUs | Needs more GPUs | Needs more GPUs |
Best for
7B–13B inference, LoRA fine-tuning, ComfyUI and Stable Diffusion.
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.
L4 vs similar GPUs
Live lowest on-demand price per GPU-hour, and price per GB of VRAM.
| GPU | VRAM | Architecture | From / hr | Per GB-hr |
|---|---|---|---|---|
| L4 (this page) | 24 GB | Ada Lovelace | $0.638 | $0.027 |
| NVIDIA RTX A5000 | 24 GB | Ampere | $0.173 | $0.007 |
| NVIDIA RTX 3090 | 24 GB | Ampere | $0.238 | $0.01 |
| NVIDIA RTX 3090 Ti | 24 GB | Ampere | $0.292 | $0.012 |
| NVIDIA RTX 4090 | 24 GB | Ada Lovelace | $0.368 | $0.015 |
| NVIDIA RTX PRO 4000 | 24 GB | Blackwell | $0.616 | $0.026 |
| NVIDIA RTX 4000 Ada SFF | 20 GB | Ada Lovelace | $0.195 | $0.01 |
L4 rental — frequently asked questions
How much does it cost to rent an NVIDIA L4 per hour?
$0.638 per GPU-hour on demand. Billing is per minute while the pod exists, so 24/7 use for a 730-hour month costs about $466 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 L4 have?
24 GB of GDDR6 at 300 GB/s of memory bandwidth. The chip is rated at up to 72 W. A pod with 9 GPUs gives 216 GB of combined VRAM for tensor- or pipeline-parallel workloads.
What size LLM can I run on an NVIDIA L4?
Roughly 9.5B parameters at FP16 or BF16, 19B at 8-bit and 38B 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 L4 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 L4 on FastInfra?
Create an account, add prepaid credit, open the GPU configurator and choose the L4, 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 L4 GPUs in one pod?
Yes, up to 9 per pod. The price scales linearly: 8 GPUs cost $5.10 per hour on Secure.
Is there a cheaper GPU than the L4 with the same VRAM?
Yes. The NVIDIA RTX A5000 has 24 GB and starts at $0.173 per hour. It differs in architecture (Ampere), memory bandwidth and multi-GPU interconnect, so compare throughput for your workload before switching.
Deploy an L4 in minutes
Price the exact pod, storage and template in the configurator, add credit, and connect over SSH or JupyterLab. Billed per minute, no commitment.