NVIDIA GeForce RTX 3080 10GB vs NVIDIA A800 PCIe 80GB

The A800 is the newer part: Ampere, launched in 2022, against the GeForce RTX 3080's Ampere from 2020. Newer architectures typically add lower-precision formats and better throughput per watt, so check the precision rows your workload actually uses.

Dense throughput for the GeForce RTX 3080 against the A800: FP64 0.5 vs 9.7 TFLOPS, FP32 30 vs 20 TFLOPS, FP16 60 vs 312 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 10 GB against 80 GB, fed at 760 GB/s versus 1.9 TB/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 320 W for the GeForce RTX 3080 and 300 W for the A800. At FP32 that works out to 0.09 against 0.07 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.