NVIDIA L40 — Specifications

Specifications Benchmarks Synonyms

Specifications

Technical data

GPU

Architecture
Ada Lovelace
Execution Units
18176
GPU Chip
AD102
L1 Cache
128 KB
L2 Cache
96 MB
Render Output Units
192
RT Cores
142
Texture Units
568

Memory

Memory Bandwidth
864 GB/s
Memory Bus
384 bit
Memory Clock
2250 MHz
Memory Data Rate
18 Gbps
Memory Size
48 GB
Memory Type
GDDR6

Clock Speeds

Base Clock
735 MHz
Boost Clock
2490 MHz

Thermal Design

System Power Supply
700 W (PSU recommendation)
TDP
300 W

Connectivity

DisplayPort Ports
4 × DisplayPort 1.4a
Max. Displays
4
PCIe Interface
PCIe 4.0 x16
Power Connectors
1x 16-pin

Featureset

CUDA
8.9
DirectX
12.2
Max. resolution
3840 × 2160
OpenCL
3.0
OpenGL
4.6
Shader Model
6.7
Vulkan
1.3

Dimensions

Length
267 mm
Slot Size
Dual-slot
Width
111 mm

Additional data

Process Technology
4 nm
Release date
Q3/2022

Theoretical Performance

FP16 (theoretical)
90.52 TFLOPS (1:1)
FP32 (theoretical)
90.52 TFLOPS
FP64 (theoretical)
1.414 GFLOPS (1:64)
Pixel Rate
478.1 GPixel/s
Texture Rate
1.414 GTexel/s

Positions in all rankings

Common positions NVIDIA L40 GPU in popular benchmarks, for comparison with other models.

No data

Benchmarks

Performance tests GPU

No benchmark results are available yet. This model is listed with specifications only.

These are saved results from the earlier catalog. Measurement dates and test configurations were not recorded. Models with no comparable results are omitted.

Recent models: test results with identified primary sources — Game frame rates

Comparable benchmark results are required to suggest performance alternatives.

Base Clock is the base GPU frequency stated by the manufacturer for this model.

Boost Clock describes automatic frequency increases. Actual clock speed varies with workload, temperature and power limits; it is not a guarantee of manual overclocking.

Rate the video card
NVIDIA L40