NVIDIA Tesla P40 24GB vs NVIDIA P100 SXM2 16GB
The Tesla P40 delivers 13% more FP32 throughput than the P100 (12 vs 11 TFLOPS dense). The Tesla P40 also carries 8 GB more memory (24 GB vs 16 GB).
NVIDIA Tesla P40 24GB
Full specs →NVIDIA P100 SXM2 16GB
Full specs →Specifications
Performance (TFLOPS)
FLOPS by Precision
What actually differs
Both GPUs launched in 2016: the Tesla P40 on Pascal and the P100 on Pascal.
Dense throughput for the Tesla P40 against the P100: FP32 12 vs 11 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.
Memory is 24 GB against 16 GB, fed at 346 GB/s versus 732 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 250 W for the Tesla P40 and 300 W for the P100. At FP32 that works out to 0.05 against 0.04 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 Tesla P40 faster than the P100?
At FP32 precision the Tesla P40 reaches 12 TFLOPS dense against 11 TFLOPS for the P100. The performance table on this page lists every published precision for both GPUs.
Which has more memory, the Tesla P40 or the P100?
The Tesla P40 carries 24 GB of VRAM versus 16 GB for the P100. Memory bandwidth is 346 GB/s for the Tesla P40 and 732 GB/s for the P100.
How much power do the Tesla P40 and the P100 draw?
The Tesla P40 is rated at 250 W TDP and the P100 at 300 W. On FP32 throughput per watt, the Tesla P40 is the more efficient part.
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.