Key Specifications
We couldn't find any available GT 710 GPUs. Search for alternative GPUs.
Frequently Asked Questions
Why choose the GT 710?
1-2GB DDR3. Display output adapter. Extremely low cost.
When is the GT 710 not a good fit?
No compute capability. Only viable as a basic display output adapter.
Are GT 710 prices going up or down?
The median on-demand price across providers has fallen about 14% since May 2025, from $0.07 to $0.06/hr per GPU. This reflects the market-wide median, which moves both when providers change prices and when lower or higher priced offerings enter the market.
What size AI models can the GT 710 run?
With 2GB of VRAM, the GT 710 is mainly limited to small quantized models and lightweight GPU workloads.
How much VRAM does the GT 710 have?
The GT 710 has 2GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.
What is the GT 710's memory bandwidth?
The GT 710 has 29 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.
What data types does the GT 710 support?
The GT 710 supports 1 precision formats. Training: FP32.
Does the GT 710 support NVLink?
No. The GT 710 is a PCIe-only GPU with no NVLink, so it is better suited to single-GPU inference and smaller-scale workloads than large distributed training jobs.
Technical Specifications
| Feature | Specification |
|---|---|
| GPU Microarchitecture | Kepler |
| CUDA Cores | 192 |
| GPU Clock speed | 902 MHz |
| Memory | 1GB DDR3 |
| Memory Clock Speed | 1600 MHz |
| Memory Bus Width | 64 bit |
| Memory Bandwidth | 14.4 GB/s |
| FP32 (float) | 366.3 GFLOPS |
| FP64 (double) | 15.26 GFLOPS |
| TDP | 19W |
| System Interface | PCI Express Gen 2 x 8 |
| CUDA Compute Capability | 3.5 |
Last updated