RTX 5090 GPU Rental
RTX 5090 GPUs on Lium have a reference price of $0.40 per GPU-hour, ideal for AI experiments and graphics at a low price point. Billed per second with no minimum, deployed in seconds from the browser or the CLI.
Price per GPU-hour
$0.40
Reference price, no pod available right now
Available now
0 pods
0 GPUs in total
Reference price
$0.40
Marketplace baseline per GPU-hour
About the RTX 5090
The RTX 5090 is NVIDIA’s Blackwell-generation flagship GeForce card. It carries 32 GB of GDDR7 at 1,792 GB/s, a third more memory and almost 80% more bandwidth than the RTX 4090, and its fifth-generation tensor cores run FP8 and FP4 natively. That extra 8 GB fits a 13B model at FP16 on one card, and leaves an image and video pipeline room to keep several models loaded at once. On Lium it is rented from independent providers by the second, with no minimum and no reservation. If you own one, you can list it on Lium and earn whenever it is rented.
What people run on it
- Inference of 7B–32B models, quantized up to 32B
- Stable Diffusion, Flux and video generation
- LoRA and QLoRA fine-tuning
- Rendering, simulation and CUDA development
RTX 5090 specifications
| VRAM | 32 GB GDDR7 |
|---|---|
| Memory bandwidth | 1,792 GB/s |
| Architecture | Blackwell |
| Released | 2025 |
What runs on one RTX 5090
With 32 GB of memory, one card holds roughly the following open models for inference, counting the 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 | 13B parameters |
| 4-bit | 34B parameters |
Running one RTX 5090 around the clock for a month (730 hours) costs about $292 at the reference price; you pay only for the seconds a pod runs.
Frequently asked questions
How much does it cost to rent an RTX 5090 on Lium?
No RTX 5090 pod is free at this moment. The marketplace reference price is $0.40 per GPU-hour; the page updates when a provider lists one.
Where is the cheapest place to rent an RTX 5090 by the hour?
No RTX 5090 pod is free on Lium at this moment; the reference price is $0.40 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 the pod when you need it, delete it when the job is done, and pay for the seconds it ran.
How do I rent an RTX 5090 pod?
Top up a balance by card or crypto, pick an RTX 5090 pod on the marketplace, choose a Docker template, add your SSH key and deploy. From a script, run lium up with the node id after exporting LIUM_API_KEY.
Where do the machines run, and what happens to my data?
Providers run their own hardware in their own facilities, and every pod on the marketplace names its city and country, so you can pick a region before you start. Your data lives on the machine you rented and is released when you delete the pod; attach a volume if you need storage that outlives a single pod.
Compare with
| GPU | VRAM | Price per GPU-hour |
|---|---|---|
| GTX 1070 | 8 GB | reference $0.37/hr |
| RTX 4090 | 24 GB | reference $0.30/hr |
| RTX 2080 SUPER | 8 GB | reference $0.74/hr |
For AI agents — CLI install, agent skill, headless signup: llms-full.txt