NVIDIA A2 16GB vs NVIDIA A800 PCIe 80GB
The A800 delivers 17.3x the FP16 throughput of the A2 (312 vs 18 TFLOPS dense). The A800 also carries 64 GB more memory (80 GB vs 16 GB).
NVIDIA A2 16GB
Full specs →NVIDIA A800 PCIe 80GB
Full specs →Specifications
Performance (TFLOPS)
FLOPS by Precision
What actually differs
The A800 is the newer part: Ampere, launched in 2022, against the A2's Ampere from 2021. 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 A2 against the A800: FP32 4.5 vs 20 TFLOPS, FP16 18 vs 312 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.
Memory is 16 GB against 80 GB, fed at 200 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 60 W for the A2 and 300 W for the A800. At FP32 that works out to 0.07 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.
Frequently asked questions
Is the A2 faster than the A800?
At FP16 precision the A800 reaches 312 TFLOPS dense against 18 TFLOPS for the A2. The performance table on this page lists every published precision for both GPUs.
Which has more memory, the A2 or the A800?
The A800 carries 80 GB of memory versus 16 GB for the A2. Memory bandwidth is 200 GB/s for the A2 and 1.9 TB/s for the A800.
How much power do the A2 and the A800 draw?
The A2 is rated at 60 W TDP and the A800 at 300 W. On FP32 throughput per watt, the A2 is the more efficient part.
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.