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
24 GB GDDR6X
Memory Bandwidth
3.35 TB/s
Memory Bandwidth
1.01 TB/s
Performance Metrics
Performance Metrics
CUDA Cores
3.1% more
16,896
CUDA Cores
16,384
FP8 Performance
3,958 TFLOPS
FP8 Performance
-
FP16 Performance
224.0% faster
267.6 TFLOPS
FP16 Performance
82.58 TFLOPS
FP32 Performance
67 TFLOPS
FP32 Performance
23.3% faster
82.58 TFLOPS
FP64 Performance
2535.7% faster
34 TFLOPS
FP64 Performance
1.29 TFLOPS
Power Consumption
700 W
Power Consumption
35.7% less
450 W