Inference
NVIDIA L40S 48GB
NVIDIA L40S with 48GB GDDR6 for LLM inference, fine-tuning, rendering, and multimodal pipelines. Strong FP8/FP16 performance in a dual-slot PCIe card with lower power than Hopper SXM modules.
Specifications
- Architecture
- NVIDIA Ada Lovelace
- GPU Memory
- 48GB GDDR6
- Memory Bandwidth
- 864 GB/s
- Form Factor
- PCIe Gen4 dual-slot
- FP8 / FP16
- Up to 1,466 / 733 TFLOPS
- TDP
- 350W
- Display
- 4× DisplayPort 1.4a
- Use case
- Inference, fine-tuning, graphics
Related products
Frontier 4019
Higher-density Blackwell system for larger local workloads.
AED 153,400
Frontier 4018
Compact Blackwell workstation for local inference and fine-tuning.
AED 76,700
Frontier 4010
Entry Blackwell system with 64GB unified memory.
AED 31,500
H100 PCIe 80GB
Genuine Hopper PCIe accelerator for dual-slot servers.
AED 114,000