NVIDIA · Ada Lovelace · L-series
24 GB of GDDR6 at 0.3 TB/s, built for inference, batch.
From $0.71/hracross 7 providers
Memory
24 GB
GDDR6
Bandwidth
0.30 TB/s
FP16 tensor
242 TFLOPS
FP8 tensor
485 TFLOPS
Interconnect
PCIe
TDP
72 W
CUDA cores
7,424
Tensor cores
232
| Provider | Type | Spot | Details |
|---|---|---|---|
 RunPod | neocloud | Yes | View |
 CoreWeave | neocloud | — | View |
 Nebius | neocloud | — | View |
 Crusoe | neocloud | — | View |
 Amazon AWS | hyperscaler | Yes | View |
 Google Cloud | hyperscaler | Yes | View |
 Oracle Cloud | hyperscaler | Yes | View |
