# 1080 Ti vs Titan V vs V100 GPU Benchmarks **URL:** \ **Category:** Technical Help\ **Created:** [January 3, 2018, 4:48pm UTC](https://deeptalk.lambda.ai/t/1080-ti-vs-titan-v-vs-v100-gpu-benchmarks/125 "2018-01-03T16:48:54Z")\ **Posts on this page:** 1\ **Showing post:** 1
**Author:** ![sabalaba](https://sea1.discourse-cdn.com/flex019/user_avatar/deeptalk.lambda.ai/sabalaba/32/4_2.png) [@sabalaba](https://deeptalk.lambda.ai/u/sabalaba)\ **Post date:** [January 3, 2018, 4:48pm UTC](https://deeptalk.lambda.ai/t/1080-ti-vs-titan-v-vs-v100-gpu-benchmarks/125/1 "2018-01-03T16:48:55Z")
# 1080 Ti vs Titan V vs V100 Here are the benchmarks comparing the GTX 1080 Ti to the new Titan V (Volta Architecture). Note that the V100 is the same chip as the Titan V so it would perform almost exactly the same. **Contributors:** Stephen Balaban [s@lambdal.com](mailto:s@lambdal.com), Chuan Li [c@lambdal.com](mailto:c@lambdal.com), Steven Clarkson [sc@lambdal.com](mailto:sc@lambdal.com) **System Software:** OS: **Ubuntu 16.04** Framework(s): **Tensorflow 1.4.1, CUDA 9, cuDNN 7** **System Hardware:** [Lambda Quad Deep Learning Workstation](https://lambdal.com/products/quad) CPU: 1x i7-6850k GPU: 4x [Titan V GPU](https://lambdal.com/products/quad), 4x 1080Ti ## Inception v3 (Synthetic Data) ![24 PM](https://us1.discourse-cdn.com/flex019/uploads/deeptalk/original/1X/057c98737d478c599a69250f020bd2015a55f28e.png) ``` Inceptionv3 (Synthetic Data) in (Images / Sec) 1080 85 1080Ti 136 Titan V 190 ``` ## VGG19 (Synthetic Data) ![07 PM](https://us1.discourse-cdn.com/flex019/uploads/deeptalk/original/1X/0774c28b22c1f9ee291492fe6043737393227712.png) ``` VGG19 (Synthetic Data) in (Images / Sec) 1080 63 1080Ti 107 Titan V 147 ``` Essentially **between 37% to 40% more throughput on the Titan V compared with the 1080Ti**. --- _[View the full topic](https://deeptalk.lambda.ai/t/1080-ti-vs-titan-v-vs-v100-gpu-benchmarks/125)._