Rent NVIDIA L40S
Ada Lovelace datacenter GPU with 48 GB of GDDR6 and ECC. Server sizes from 1 to 8 GPUs, billed by the hour. Pay in crypto, no KYC, root over SSH.
Live price by server size
Loading live data…| GPUs | Per GPU-hour | Server, per hour | Availability | Action |
|---|
Interruptible (spot)
| GPUs | Per GPU-hour | Server, per hour | Action |
|---|
Price history
Use the left and right arrow keys to read values at each point in time.
| Time (UTC) | Best 1-GPU hourly price | Free cards |
|---|
What you can run on the L40S
The NVIDIA L40S is an Ada Lovelace datacenter GPU with 48 GB of GDDR6 memory with ECC and hardware FP8 support. It covers inference, image and video generation and fine-tuning on a single card. Rent it here by the hour, paid in crypto, with root access over SSH.
Typical tasks
- Inference of mid-size language models, in FP8 or quantized
- Image and video generation such as Stable Diffusion and Flux
- LoRA fine-tuning
- Workloads where ECC memory matters
- Batch jobs: embeddings, evaluation
What fits
A rough inference guide, in billions of parameters: weights only, about 20% left for context; real limits depend on context length and the serving engine. It assumes the weights take up to 80% of the total memory, at 2 bytes per parameter for BF16, 1 byte for FP8 and half a byte for 4-bit. With several cards, the serving engine splits the model across them.
| GPUs | BF16 | FP8 | 4-bit |
|---|---|---|---|
| 1 GPU | 19B | 38B | 76B |
| 2 GPUs | 38B | 76B | 153B |
| 4 GPUs | 76B | 153B | 307B |
| 8 GPUs | 153B | 307B | 614B |
Based on 48 GB per card.
How to rent the L40S
- Sign inSign in with your e-mail. No KYC: you pay from your own wallet.
- QuoteWe confirm the machine and the price within 1 hour, 03:00–23:00 UTC.
- PayYou approve a quote before anything is charged. Pay in USDC on Ethereum today; more tokens are coming.
- KeysAfter payment we test the server and send you SSH access.
Billed by the hour, no minimum term. Reserved terms for a month, a quarter or a year are quoted by hand and cost less per hour.
Open the order formBuilding for clients? See the partner program. AI agent? llms.txt describes the public price file and the order link.
L40S FAQ
What size of model fits on one L40S?
As a rough guide for inference, with the weights taking up to 80% of the 48 GB: about 19B parameters at BF16, 38B at FP8 and 76B at 4-bit on a single card. Real limits depend on the context length and the serving engine. The What fits table on this page also covers 2, 4 and 8 cards.
How much memory does the L40S have, and is it ECC?
48 GB of GDDR6 per card, with ECC. The Specs section on this page shows the figure the cards on offer report right now.
Does the L40S support FP8?
Yes. The L40S is an Ada Lovelace GPU with hardware FP8 support.
Can I rent more than one L40S in a server?
Yes. Servers come with 1, 2, 4 or 8 GPUs. The live table at the top of this page shows which sizes are offered right now; a size that is not offered can be asked for and is quoted by hand.
Do I need KYC?
No. You sign in with your e-mail and pay from your own wallet.