HyperAI
Command Palette
Search for a command to run...
GPU Comparison
Compare GPU performance benchmarks side by side
Basic Information
Basic Information
Release Date
Nov 2024
Release Date
Mar 2023
Architecture
NVIDIA Hopper
Architecture
NVIDIA Hopper
Memory
141 GB HBM3
Memory
80 GB HBM3
Memory Bandwidth
4.89 TB/s
Memory Bandwidth
2.04 TB/s
Performance Metrics
Performance Metrics
CUDA Cores
16,896
CUDA Cores
16,896
FP8 Performance
-
FP8 Performance
3,026 TFLOPS
FP16 Performance
17.8% faster
241.3 TFLOPS
FP16 Performance
204.9 TFLOPS
FP32 Performance
17.1% faster
60 TFLOPS
FP32 Performance
51.22 TFLOPS
FP64 Performance
17.1% faster
30 TFLOPS
FP64 Performance
25.61 TFLOPS
Power Consumption
600 W
Power Consumption
41.7% less
350 W

