L40

The NVIDIA L40 uses the Ada Lovelace architecture with 48 GB of GDDR6 VRAM. It is designed for datacenter scalability across AI inference, visual computing, and rendering workloads, offering a balanced profile for organizations with diverse GPU compute requirements.

Its 48 GB of VRAM supports Large Language Models (LLM) and fine-tuning of mid-sized models, along with graphics-intensive rendering and simulation tasks. The L40 serves as a flexible datacenter accelerator for teams that need to run both AI and visualization workloads on shared infrastructure.