NVIDIA Quadro P2000 5GB vs NVIDIA GeForce GTX 1080 Ti 11GB

Both GPUs launched in 2017: the Quadro P2000 on Pascal and the GeForce GTX 1080 Ti on Pascal.

Dense throughput for the Quadro P2000 against the GeForce GTX 1080 Ti: FP32 3 vs 11 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 5 GB against 11 GB, fed at 140 GB/s versus 484 GB/s. More memory per GPU means larger models fit before you have to shard across cards, which often matters more than raw TFLOPS for inference.

Power budgets are 75 W for the Quadro P2000 and 250 W for the GeForce GTX 1080 Ti. At FP32 that works out to 0.04 against 0.05 TFLOPS per watt.

For LLM training and inference, weight the FP8 and FP16 rows and memory capacity most heavily. For scientific and HPC workloads, the FP64 row is the one to read.