GPU Wiki
Compare NVIDIA GPUs
Select up to four GPU Wiki entries to compare matching specifications row by row. The comparison uses the site database and keeps generation-specific specs visibly separate.
Row order:
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.
| Spec | L20 |
|---|---|
| Overview | |
| Product name | NVIDIA L20 |
| Architecture | Ada Lovelace |
| Generation / family | NVIDIA L-Series |
| GPU codename | AD102 |
| Launch date | 2023-11-16 |
| Market segment | Data Center in NVIDIA L-Series |
| Board type / entry type | Data Center GPU |
| GPU | |
| Process node | TSMC 5 nm |
| Die size | 609 mm² |
| Transistor count | 76.3 billion |
| GPU chip | AD102 |
| SM / multiprocessor count | 92 |
| CUDA Cores | 11776 |
| Tensor Cores | 368 |
| RT Cores | 92 |
| ROPs | 128 |
| TMUs | 368 |
| Clocks | |
| Base / Core clock | 1,440 MHz |
| Boost clock | 2,520 MHz |
| Memory clock | 2,250 MHz |
| Memory | |
| Memory size | 48 GB |
| Memory type | GDDR6 |
| Memory bus width | 384-bit |
| Memory bandwidth | 864 GB/s |
| Bus / Interface | |
| Bus interface | PCIe 4.0 x16 |
| AGP / PCI / PCIe distinction | PCIe |
| Power | |
| TDP / TBP / board power | 275 W |
| Recommended PSU | 600 W |
| Power connectors | 1x 16-pin |
| Slot width | Dual-slot, 267 mm length |
| Display / Media | |
| Display outputs | 4x DisplayPort 1.4a |
| Features | |
| DirectX support | DirectX 12.2 |
| OpenGL support | OpenGL 4.6 |
| Vulkan support | Vulkan 1.4 |
| CUDA support | 8.9 |
| Shader Model | 6.8 |
| Ray tracing support | Hardware RT units present |
| Performance / Benchmarks | |
| FP32 throughput | 59.35 TFLOPS |
| FP16 throughput | 59.35 TFLOPS |
Overview
Product name
L20
NVIDIA L20
Architecture
L20
Ada Lovelace
Generation / family
L20
NVIDIA L-Series
GPU codename
L20
AD102
Launch date
L20
2023-11-16
Market segment
L20
Data Center in NVIDIA L-Series
Board type / entry type
L20
Data Center GPU
GPU
Process node
L20
TSMC 5 nm
Die size
L20
609 mm²
Transistor count
L20
76.3 billion
GPU chip
L20
AD102
SM / multiprocessor count
L20
92
CUDA Cores
L20
11776
Tensor Cores
L20
368
RT Cores
L20
92
ROPs
L20
128
TMUs
L20
368
Clocks
Base / Core clock
L20
1,440 MHz
Boost clock
L20
2,520 MHz
Memory clock
L20
2,250 MHz
Memory
Memory size
L20
48 GB
Memory type
L20
GDDR6
Memory bus width
L20
384-bit
Memory bandwidth
L20
864 GB/s
Bus / Interface
Bus interface
L20
PCIe 4.0 x16
AGP / PCI / PCIe distinction
L20
PCIe
Power
TDP / TBP / board power
L20
275 W
Recommended PSU
L20
600 W
Power connectors
L20
1x 16-pin
Slot width
L20
Dual-slot, 267 mm length
Display / Media
Display outputs
L20
4x DisplayPort 1.4a
Features
DirectX support
L20
DirectX 12.2
OpenGL support
L20
OpenGL 4.6
Vulkan support
L20
Vulkan 1.4
CUDA support
L20
8.9
Shader Model
L20
6.8
Ray tracing support
L20
Hardware RT units present
Performance / Benchmarks
FP32 throughput
L20
59.35 TFLOPS
FP16 throughput
L20
59.35 TFLOPS