HyperAI
Command Palette
Search for a command to run...
GPU Comparison
Compare GPU performance benchmarks side by side
Basic Information
Basic Information
Release Date
Jun 2025
Release Date
Jan 2025
Architecture
CDNA4
Architecture
NVIDIA Blackwell
Memory
288 GB HBM3E
Memory
32 GB GDDR7
Memory Bandwidth
8.19 TB/s
Memory Bandwidth
1.79 TB/s
Performance Metrics
Performance Metrics
CUDA Cores
1,024
CUDA Cores
2025.0% more
21,760
FP8 Performance
-
FP8 Performance
-
FP16 Performance
50.1% faster
157.3 TFLOPS
FP16 Performance
104.8 TFLOPS
FP32 Performance
50.1% faster
157.3 TFLOPS
FP32 Performance
104.8 TFLOPS
FP64 Performance
4692.7% faster
78.6 TFLOPS
FP64 Performance
1.64 TFLOPS
Power Consumption
1400 W
Power Consumption
58.9% less
575 W