NVIDIA GH200 Superchip kontra NVIDIA GeForce RTX 3080 Ti — Porównanie GPU (Apr 2026)
NVIDIA GH200 Superchip (96GB HBM3, 989 TFLOPS FP16, Hopper) vs NVIDIA GeForce RTX 3080 Ti (12GB GDDR6X, 34.1 TFLOPS FP16, Ampere)
|
NVIDIA GH200 Superchip
96GB HBM3 · Hopper
|
NVIDIA GeForce RTX 3080 Ti
12GB GDDR6X · Ampere
|
||
|---|---|---|---|
| Specyfikacje | |||
| Producent | NVIDIA | NVIDIA | |
| Architektura | Hopper | Ampere | |
| VRAM | 96 GB HBM3 | 12 GB GDDR6X | |
| Przepustowość | 4,000 GB/s | 912 GB/s | |
| FP16 (Tensor) | 989.0 TFLOPS | 34.1 TFLOPS | |
| FP32 | 494.5 TFLOPS | 17.0 TFLOPS | |
| TDP | 700W | 350W | |
| Rok wydania | 2023 | 2021 | |
| Segment | Data center | Consumer | |
| Najlepsze do | Large-scale AI training HPC | Gaming inference | |
| Cennik w chmurze | |||
| Najtańsze na żądanie | — | — | |
| Najtańsze spot | — | — | |
| Dostawcy | 0 | 0 | |
NVIDIA GH200 Superchip
NVIDIA GeForce RTX 3080 Ti