RTX 3070

Every provider's rate, side by side.

RTX 3070 is available through the OneInfer GPU marketplace with live provider pricing, regions, VRAM, and deployment options from the API.

3 providers list it in 10 regions, from $0.07 per GPU-hour with vastai. It has 8 GB of GPU memory. Pick a provider and region, deploy it from the OneInfer Console with your own Docker image, connect over SSH, and pay from one pay-as-you-go wallet while it runs.

Deploy the RTX 3070 in 4 steps

Step 1 of 4

3 providers list the RTX 3070, from $0.07 per GPU-hour. The table below sorts them by price.

Cloud GPU
VRAM
8GB
CUDA cores
N/A
TDP
N/A
Bandwidth
N/A
Process node
N/A
Launch date
N/A

Available from 3 providers

Sorted by price. Select the price heading to re-sort.

RTX 3070 providers, regions, configurations and hourly prices
ProviderRegionsConfigAvailabilityDeploy
vastaivastai
US-CA-01, US-FL-01, US-IL-01, CA-QC-01, EU-RO-01, EU-SE-01, AS-TW-01, US-UT-01, AS-VN-01, US-VA-011x 8GB$0.07Available
vastaivastai
US-CA-01, CA-QC-01, AS-VN-01, US-VA-012x 8GB$0.16Available
vastaivastai
CA-QC-01, US-VA-014x 8GB$0.43Available

Full specifications

Data from GPU specs and provider APIs

AI TOPS
N/A
FP8 TFLOPS
N/A
FP16 TFLOPS
N/A
BF16 TFLOPS
N/A
FP32 TFLOPS
N/A
INT8 TOPS
N/A
Sparse multiplier
N/A

Benchmarks

RTX 3070 vs comparable GPUs on the platform

Inference throughput

7B model, tokens per second

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

Ready to deploy RTX 3070?

Deploy from your choice of 3 providers.