NVIDIA Titan RTX 24GB vs NVIDIA GeForce RTX 2080 Super 8GB

The GeForce RTX 2080 Super is the newer part: Turing, launched in 2019, against the Titan RTX's Turing from 2018. 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 Titan RTX against the GeForce RTX 2080 Super: FP64 0.5 vs 0.3 TFLOPS, FP32 16 vs 11 TFLOPS, FP16 131 vs 45 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 24 GB against 8 GB, fed at 672 GB/s versus 496 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 280 W for the Titan RTX and 250 W for the GeForce RTX 2080 Super. At FP32 that works out to 0.06 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.