- Home
- Compare GPUs
- NVIDIA GeForce RTX 4090 vs NVIDIA L20
NVIDIA GeForce RTX 4090 vs NVIDIA L20
Side-by-side comparison of specifications, performance, and efficiency.
NVIDIA GeForce RTX 4090
Architecture
Ada Lovelace
Year
2022
VRAM
24 GB
TDP
450 W
NVIDIA L20
Architecture
Ada Lovelace
Year
2024
VRAM
48 GB
TDP
275 W
Specifications
NVIDIA GeForce RTX 4090 NVIDIA L20
Architecture
Ada Lovelace Ada Lovelace
Launch Year
2022 2024
Form Factor
PCIe PCIe
VRAM
24 GB48 GB
Memory Bandwidth
1.0 TB/s864 GB/s
TDP
450 W275 W
Process Node
4nm —
| Spec | NVIDIA GeForce RTX 4090 | NVIDIA L20 |
|---|---|---|
| Architecture | Ada Lovelace | Ada Lovelace |
| Launch Year | 2022 | 2024 |
| Form Factor | PCIe | PCIe |
| VRAM | 24 GB | 48 GB |
| Memory Bandwidth | 1.0 TB/s | 864 GB/s |
| TDP | 450 W | 275 W |
| Process Node | 4nm | — |
Performance (TFLOPS)
NVIDIA GeForce RTX 4090 NVIDIA L20
FP64
1.3 TFlops —
FP32
82.6 TFlops 59.8 TFlops
FP16
165.2 TFlops
sparse not published
119.5 TFlops sparse not published
BF16
165.2 TFlops
sparse not published
119.5 TFlops sparse not published
FP8
330.3 TFlops
sparse not published
239.0 TFlops sparse not published
INT8
330.3 TFlops
sparse not published
239.0 TFlops sparse not published
| Precision | NVIDIA GeForce RTX 4090 | NVIDIA L20 |
|---|---|---|
| FP64 | 1.3 TFlops | — |
| FP32 | 82.6 TFlops | 59.8 TFlops |
| FP16 | 165.2 TFlops sparse not published | 119.5 TFlops sparse not published |
| BF16 | 165.2 TFlops sparse not published | 119.5 TFlops sparse not published |
| FP8 | 330.3 TFlops sparse not published | 239.0 TFlops sparse not published |
| INT8 | 330.3 TFlops sparse not published | 239.0 TFlops sparse not published |
FLOPS by Precision
Efficiency — TDP vs FP32 Performance
Analysis
Most Efficient
NVIDIA
L20
0.22 TFLOPS/W
Where to Rent
NVIDIA GeForce RTX 4090
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.