NVIDIA L40 vs NVIDIA GeForce RTX 3070 Ti — GPU-Vergleich (Apr 2026)
NVIDIA L40 (48GB GDDR6, 181 TFLOPS FP16, Ada Lovelace) vs NVIDIA GeForce RTX 3070 Ti (8GB GDDR6X, 21.7 TFLOPS FP16, Ampere)
|
NVIDIA L40
48GB GDDR6 · Ada Lovelace
|
NVIDIA GeForce RTX 3070 Ti
8GB GDDR6X · Ampere
|
||
|---|---|---|---|
| Spezifikationen | |||
| Hersteller | NVIDIA | NVIDIA | |
| Architektur | Ada Lovelace | Ampere | |
| VRAM | 48 GB GDDR6 | 8 GB GDDR6X | |
| Bandbreite | 864 GB/s | 608 GB/s | |
| FP16 (Tensor) | 181.0 TFLOPS | 21.7 TFLOPS | |
| FP32 | 90.5 TFLOPS | 10.8 TFLOPS | |
| TDP | 300W | 290W | |
| Erscheinungsjahr | 2023 | 2021 | |
| Segment | Data center | Consumer | |
| Am besten geeignet für | Inference video processing rendering | Budget inference gaming | |
| Cloud-Preise | |||
| Günstigste On-Demand | — | — | |
| Günstigste Spot | — | — | |
| Anbieter | 0 | 0 | |
NVIDIA L40
NVIDIA GeForce RTX 3070 Ti