L40 GPU Rental
L40 GPUs on Lium have a reference price of $0.33 per GPU-hour, built for large-scale AI training, inference, and HPC. Billed per second, no minimum. Deploy in seconds from the browser or the CLI.
Refer a friend: earn 5% of their top-ups for 3 months, then 2.5% for 3 more. Get your link
Prices and availability as of 02:33 UTC
Price per GPU-hour
$0.33
Reference price, no pod free now
Available now
0 pods
0 GPUs in total
Reference price
$0.33
Marketplace baseline per GPU-hour
About the L40
The L40 is an Ada-generation NVIDIA data center GPU, built for large-scale AI training, inference, and HPC. Released in 2022, it carries 48 GB of GDDR6 at 864 GB/s, which sets how large a model fits on one card and how fast its weights stream. On Lium it is rented from independent providers by the second, with no minimum and no reservation, from the browser or the CLI.
Common uses
- Training and fine-tuning language models
- High-throughput LLM inference
- Multi-GPU jobs in one node
- HPC and scientific computing
L40 specifications
| VRAM | 48 GB GDDR6 |
|---|---|
| Memory bandwidth | 864 GB/s |
| Architecture | Ada |
| Released | 2022 |
What runs on one L40
The largest open models one 48 GB card holds for inference (weights plus about 20% for activations and cache). Rent several GPUs in one pod to go bigger.
| Precision | Largest model that fits |
|---|---|
| FP16 | 13B parameters |
| 8-bit | 34B parameters |
| 4-bit | 70B parameters |
Running one L40 around the clock for a month (730 hours) costs about $241 at the reference price; you pay only for the seconds a pod runs.
Frequently asked questions
How much does it cost to rent an L40 on Lium?
No L40 pod is free at this moment. The marketplace reference price is $0.33 per GPU-hour; the page updates when a provider lists one.
Where is the cheapest place to rent an L40 by the hour?
No L40 pod is free on Lium at this moment; the reference price is $0.33 per GPU-hour, billed per second with no minimum once a provider lists one.
Is there a minimum rental period?
No. Lium bills per second with no minimum and no reservation: start a pod when you need it, delete it when done, and pay for the seconds it ran.
How do I rent an L40 pod?
Top up by card or crypto, pick an L40 pod on the marketplace, choose a Docker template, add your SSH key and deploy. From a script: export LIUM_API_KEY, then run lium up with the node id.
Where do the machines run, and what happens to my data?
Providers run their own hardware in their own facilities, and every pod names its city and country, so you pick the region. Your data stays on the rented machine and is released when you delete the pod; attach a volume for storage that outlives a pod.
Compare with
| GPU | VRAM | Price per GPU-hour |
|---|---|---|
| A800 80GB PCIe | 80 GB | reference $0.31/hr |
| CMP 170HX | 8 GB | from $0.37/hr |
| Graphics Device | - | from $0.50/hr |
For AI agents (CLI install, agent skill, headless signup): llms-full.txt