NVIDIA V100 SXM2 32GB vs NVIDIA V100 PCIe 32GB
The V100 SXM2 32GB delivers 12% more FP16 throughput than the V100 PCIe 32GB (125 vs 112 TFLOPS dense).
NVIDIA V100 SXM2 32GB
Full specs →NVIDIA V100 PCIe 32GB
Full specs →Specifications
Performance (TFLOPS)
FLOPS by Precision
What actually differs
Both GPUs launched in 2018: the V100 SXM2 32GB on Volta and the V100 PCIe 32GB on Volta.
Dense throughput for the V100 SXM2 32GB against the V100 PCIe 32GB: FP64 7.8 vs 7 TFLOPS, FP32 16 vs 14 TFLOPS, FP16 125 vs 112 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.
Memory is 32 GB against 32 GB, fed at 900 GB/s versus 900 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 300 W for the V100 SXM2 32GB and 250 W for the V100 PCIe 32GB. At FP32 that works out to 0.05 against 0.06 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 V100 SXM2 32GB faster than the V100 PCIe 32GB?
At FP16 precision the V100 SXM2 32GB reaches 125 TFLOPS dense against 112 TFLOPS for the V100 PCIe 32GB. The performance table on this page lists every published precision for both GPUs.
Which has more memory, the V100 SXM2 32GB or the V100 PCIe 32GB?
Both GPUs carry 32 GB of VRAM. Memory bandwidth is 900 GB/s for the V100 SXM2 32GB and 900 GB/s for the V100 PCIe 32GB.
How much power do the V100 SXM2 32GB and the V100 PCIe 32GB draw?
The V100 SXM2 32GB is rated at 300 W TDP and the V100 PCIe 32GB at 250 W. On FP32 throughput per watt, the V100 PCIe 32GB is the more efficient part.
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.