Infrastructure atlas
NVIDIA/Ada Lovelace
L40S
A PCIe data-center GPU for generative AI inference, rendering, video, and multimodal workloads without NVLink or MIG.
GPUAdainferencevideorendering

Precision & peak compute
| Precision | Published peak | Basis |
|---|---|---|
| FP8 Tensor | 733 TFLOPS | Dense |
| FP8 Tensor | 1,466 TFLOPS | Sparse |
| FP16 / BF16 Tensor | 362 TFLOPS | Dense |
| INT8 Tensor | 733 TOPS | Dense |
| FP32 | 91.6 TFLOPS | Dense |
Peak FLOPS and TOPS are theoretical hardware figures. Sparse and dense modes, chip and system totals, and form factors are not interchangeable.
NVIDIA L40S specifications