RentServersBy the RentServers team at Wells Software Consulting LLC · Updated
L40S specifications
| Architecture | Ada Lovelace |
|---|---|
| Memory | 48 GB GDDR6 (ECC) |
| Memory bandwidth | 864 GB/s |
| FP8 Tensor (dense) | ~733 TFLOPS |
| Interconnect | PCIe Gen4, no NVLink |
| Max power | 350 W |
Figures for the SXM/HGX version unless noted, from NVIDIA. Dense Tensor Core throughput; NVIDIA's headline numbers with sparsity are double.
Good fits
- Serving 7B–13B models, or quantized models up to about 30B on a single card.
- Diffusion image and video generation.
- Rendering and graphics workloads that use its RT cores.
Poor fits
Multi-GPU training. Without NVLink, GPUs communicate over PCIe, which bottlenecks tensor parallelism. Use H100 or A100 SXM servers for that.
L40S questions
How much does it cost to rent an L40S?
GetDeploying's tracker (October 16, 2026) shows a median of $1.50 per GPU-hour on demand and $1.09 reserved, with in-stock offers from $0.55.