Most deployedCloud GPU
A16
A16 is available through OneInfer GPU marketplace with live provider pricing, regions, VRAM, and deployment options from the API.
VRAM
16GB
Best price
$0.06/gpu/hr
Providers
4 available
Regions
8 regions
VRAM
16GB
CUDA cores
1,280
TDP
250W
Bandwidth
N/A
Process node
8nm
Launch date
N/A
Available from 4 providers
Sorted by price · click price to re-sort| Provider | Regions | Config | Price / hr ▾ | Availability | |
|---|---|---|---|---|---|
 vultr | US-IL-01, US-GA-01, DE-HE-01, US-CA-02, AS-SG-02, IN-KA-01 | 1x 16GB | $0.06 | Limited | |
| vultr | US-NY-01, US-IL-01, US-CA-02, JP-TYO-02, AS-SG-02, IN-KA-01 | 1x 16GB | $0.12 | Limited | |
| vultr | US-CA-02, JP-TYO-02, AS-SG-02, IN-KA-01 | 1x 16GB | $0.24 | Limited | |
| vultr | US-CA-02 | 1x 16GB | $0.94 | Limited |
Full specifications
Data from GPU specs and provider APIsAI TOPS0
FP8 TFLOPS0
FP16 TFLOPS4.493
BF16 TFLOPS0
FP32 TFLOPS4.493
INT8 TOPS0
Sparse multiplier2
Benchmarks
A16 vs comparable GPUs on the platformInference throughput
7B model · tokens/sec
B200 SXM15,000
H200 SXM8,500
H100620
A100500
GeForce RTX 5090180
Training performance
Overall training multiplier
B200 SXM30x
H200 SXM18x
H10015x
A1003.4x
L40S2.8x
GeekBench OpenCL
Compute benchmark score
GeForce RTX 5090367,740
H200 SXM343,598
L40S337,706
H100336,474
B200 SXM333,768
Best for
LLM fine-tuningHigh-throughput inferenceMulti-modal model trainingLarge-batch distributed trainingRAG pipelines at scale
Similar GPUs
Ready to deploy A16?
Spin up an instance in minutes from your choice of 4 providers.