NVIDIA RTX A2000 12GB vs NVIDIA A800 PCIe 80GB

Both GPUs launched in 2022: the RTX A2000 on Ampere and the A800 on Ampere.

Dense throughput for the RTX A2000 against the A800: FP64 0.1 vs 9.7 TFLOPS, FP32 8 vs 20 TFLOPS, FP16 8 vs 312 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 12 GB against 80 GB, fed at 288 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 70 W for the RTX A2000 and 300 W for the A800. At FP32 that works out to 0.11 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.