NVIDIA L40S
by NVIDIA · paid · Last verified 2026-03-17
The NVIDIA L40S is a universal data center GPU based on the Ada Lovelace architecture. It features 48GB of GDDR6 memory and combines powerful AI compute, graphics, and media acceleration capabilities, making it a versatile solution for a wide range of workloads from generative AI to professional visualization.
https://www.nvidia.com/en-us/data-center/l40s/ ↗B
B—Above Average
Adoption: B+Quality: AFreshness: B+Citations: BEngagement: F
Specifications
- License
- Proprietary
- Pricing
- paid
- Capabilities
- Generative AI and LLM Inference, High-Fidelity Professional Visualization, Real-Time Ray Tracing (3rd-gen RT Cores), Accelerated AI Training and Inference (4th-gen Tensor Cores), FP8 and FP16 Compute, High-Throughput Video Transcoding and Streaming, AV1 Encode and Decode, Digital Twin and Simulation via NVIDIA Omniverse, High-Performance Computing (HPC)
- Integrations
- NVIDIA AI Enterprise, NVIDIA Omniverse, CUDA Toolkit, TensorRT, NVIDIA Triton Inference Server, Standard PCIe Gen4 server chassis from OEMs (Dell, HPE, Lenovo, Supermicro), VMware vSphere with NVIDIA AI Enterprise
- Use Cases
- [object Object], [object Object], [object Object], [object Object], [object Object]
- API Available
- No
- Tags
- gpu, data-center, inference, ada-lovelace, universal-accelerator, generative-ai, llm, ray-tracing, digital-twin, video-transcoding, pcie
- Added
- 2026-03-17
- Completeness
- 0.9%
Index Score
63.4Adoption
72
Quality
88
Freshness
78
Citations
68
Engagement
0