Architecture
NVIDIA Ada Lovelace Architecture
Process Size
4nm NVIDIA Custom Process | TSMC
Die Size
294.5 mm2
Translators
35.8 Billion
CUDA Cores
6144
Tensor Cores
192 | Gen 4
RT Cores
48 | Gen 3
FP32 Performance
19.2 TFLOPS
Tensor Performance
306.8 TFLOPS
Single-Precision Performance1