L40 — Full Specifications

nvidia Ada Lovelace · FP32: 90.52 TFLOPS · Memory: 48.0 GB GDDR6 · TDP: 300.0W

Last updated:

Calculated from published specifications — a Quanteta index, not measured FPS / benchmark results.

Quanteta Performance Indices

QOV ? Overall Performance Index 35.1 / 100 top 1%
QAI ? Compute (AI) Strength 8.9 / 100 top 5%
QGP ? Graphics Index 74.1 / 100 top 1%
QWP ? Power Efficiency Index 50.8 / 100 top 1%
QME ? Memory Bandwidth Density 0.3 / 100 top 56%

Methodology

Full Specifications

GPU ID
nvidia-l40
Vendor
nvidia
Manufacturer
NVIDIA
GPU Chip
AD102
Architecture
Ada Lovelace
Generation
Server Ada(Lxx)
Process
5.0nm
Transistors
76.3B
Die Size
609.0 mm²
Release
2022-10-13
Bus Interface
PCIe 4.0 x16
Base Clock
735.0 MHz
Boost Clock
2490.0 MHz
Memory
48.0 GB GDDR6
Memory Bus
384.0-bit
Bandwidth
864.0 GB/s
Shaders
18176.0
TMUs
568.0
ROPs
192.0
Tensor Cores
568.0
RT Cores
142.0
TDP
300.0W
FP32
90.52 TFLOPS
FP16
90.52 TFLOPS
FP64
1.41 TFLOPS
Source
TechPowerUp
Check price on Amazon

Search link to Amazon.co.jp. We do not collect price or stock data — Amazon shows the current price and availability. As an Amazon Associate, Quanteta earns from qualifying purchases.

Related GPUs

GPUs with the closest value on each axis. A descriptive neighbourhood derived from the calculated indices — not a recommendation.

Closest Overall Performance Index

L40G 35.0 QOV 35.0 / 100 L40 CNX 35.0 QOV 35.0 / 100 RTX 6000 Ada Generation 35.4 QOV 35.4 / 100

Closest Compute (AI) Strength

L40 CNX 8.9 QAI 8.9 / 100 L40G 8.9 QAI 8.9 / 100 Radeon RX 7900 XT 8.8 QAI 8.8 / 100

Closest Graphics Index

L40G 73.7 QGP 73.7 / 100 L40 CNX 73.7 QGP 73.7 / 100 RTX 6000 Ada Generation 74.8 QGP 74.8 / 100

Closest Memory Bandwidth

L20 864 GB/s QME 0.3 / 100 L40 CNX 864 GB/s QME 0.4 / 100 L40G 864 GB/s QME 0.4 / 100
Compare · ← Back to all GPUs