NVIDIA · Ampere · A-series
24 GB of GDDR6 at 0.6 TB/s, built for inference.
From $0.75/hracross 8 providers
Memory
24 GB
GDDR6
Bandwidth
0.60 TB/s
FP16 tensor
250 TFLOPS
FP8 tensor
—
no FP8 path
Interconnect
PCIe
TDP
150 W
CUDA cores
9,216
Tensor cores
288
| Provider | Type | Spot | Details |
|---|---|---|---|
 RunPod | neocloud | Yes | View |
 Vast.ai | marketplace | Yes | View |
 Lambda | neocloud | — | View |
 Crusoe | neocloud | — | View |
 Amazon AWS | hyperscaler | Yes | View |
 Google Cloud | hyperscaler | Yes | View |
 Microsoft Azure | hyperscaler | Yes | View |
 Oracle Cloud | hyperscaler | Yes | View |
