HyperAI
Command Palette
Search for a command to run...
GPU Comparison
Compare GPU performance benchmarks side by side
Basic Information
Basic Information
Release Date
Mar 2023
Release Date
Oct 2022
Architecture
NVIDIA Hopper
Architecture
NVIDIA Ada Lovelace
Memory
80 GB HBM3
Memory
48 GB GDDR6
Memory Bandwidth
2.04 TB/s
Memory Bandwidth
864 GB/s
Performance Metrics
Performance Metrics
CUDA Cores
20.0% more
16,896
CUDA Cores
14,080
FP8 Performance
3,026 TFLOPS
FP8 Performance
-
FP16 Performance
126.4% faster
204.9 TFLOPS
FP16 Performance
90.52 TFLOPS
FP32 Performance
51.22 TFLOPS
FP32 Performance
76.7% faster
90.52 TFLOPS
FP64 Performance
1716.3% faster
25.61 TFLOPS
FP64 Performance
1.41 TFLOPS
Power Consumption
350 W
Power Consumption
14.3% less
300 W