NVIDIA GeForce GTX 1080 8GB vs NVIDIA Tesla P40 24GB
The Tesla P40 delivers 35% more FP32 throughput than the GeForce GTX 1080 (12 vs 8.9 TFLOPS dense). The Tesla P40 also carries 16 GB more memory (24 GB vs 8 GB).
NVIDIA GeForce GTX 1080 8GB
Full specs →NVIDIA Tesla P40 24GB
Full specs →Specifications
Performance (TFLOPS)
FLOPS by Precision
What actually differs
Both GPUs launched in 2016: the GeForce GTX 1080 on Pascal and the Tesla P40 on Pascal.
Dense throughput for the GeForce GTX 1080 against the Tesla P40: FP32 8.9 vs 12 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.
Memory is 8 GB against 24 GB, fed at 320 GB/s versus 346 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 180 W for the GeForce GTX 1080 and 250 W for the Tesla P40. At FP32 that works out to 0.05 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.
Frequently asked questions
Is the GeForce GTX 1080 faster than the Tesla P40?
At FP32 precision the Tesla P40 reaches 12 TFLOPS dense against 8.9 TFLOPS for the GeForce GTX 1080. The performance table on this page lists every published precision for both GPUs.
Which has more memory, the GeForce GTX 1080 or the Tesla P40?
The Tesla P40 carries 24 GB of memory versus 8 GB for the GeForce GTX 1080. Memory bandwidth is 320 GB/s for the GeForce GTX 1080 and 346 GB/s for the Tesla P40.
How much power do the GeForce GTX 1080 and the Tesla P40 draw?
The GeForce GTX 1080 is rated at 180 W TDP and the Tesla P40 at 250 W. On FP32 throughput per watt, the GeForce GTX 1080 is the more efficient part.
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.