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 | L40 |
|---|---|
| Overview | |
| Product name | NVIDIA L40 |
| Architecture | Ada Lovelace |
| Generation / family | NVIDIA L-Series |
| GPU codename | AD102 |
| Launch date | 2022-10-13 |
| 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 | 142 |
| CUDA Cores | 18176 |
| Tensor Cores | 568 |
| RT Cores | 142 |
| ROPs | 192 |
| TMUs | 568 |
| Clocks | |
| Base / Core clock | 735 MHz |
| Boost clock | 2,490 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 | 300 W |
| Recommended PSU | 700 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 | 90.52 TFLOPS |
| FP16 throughput | 90.52 TFLOPS |
Overview
Product name
L40
NVIDIA L40
Architecture
L40
Ada Lovelace
Generation / family
L40
NVIDIA L-Series
GPU codename
L40
AD102
Launch date
L40
2022-10-13
Market segment
L40
Data Center in NVIDIA L-Series
Board type / entry type
L40
Data Center GPU
GPU
Process node
L40
TSMC 5 nm
Die size
L40
609 mm²
Transistor count
L40
76.3 billion
GPU chip
L40
AD102
SM / multiprocessor count
L40
142
CUDA Cores
L40
18176
Tensor Cores
L40
568
RT Cores
L40
142
ROPs
L40
192
TMUs
L40
568
Clocks
Base / Core clock
L40
735 MHz
Boost clock
L40
2,490 MHz
Memory clock
L40
2,250 MHz
Memory
Memory size
L40
48 GB
Memory type
L40
GDDR6
Memory bus width
L40
384-bit
Memory bandwidth
L40
864 GB/s
Bus / Interface
Bus interface
L40
PCIe 4.0 x16
AGP / PCI / PCIe distinction
L40
PCIe
Power
TDP / TBP / board power
L40
300 W
Recommended PSU
L40
700 W
Power connectors
L40
1x 16-pin
Slot width
L40
Dual-slot, 267 mm length
Display / Media
Display outputs
L40
4x DisplayPort 1.4a
Features
DirectX support
L40
DirectX 12.2
OpenGL support
L40
OpenGL 4.6
Vulkan support
L40
Vulkan 1.4
CUDA support
L40
8.9
Shader Model
L40
6.8
Ray tracing support
L40
Hardware RT units present
Performance / Benchmarks
FP32 throughput
L40
90.52 TFLOPS
FP16 throughput
L40
90.52 TFLOPS