NVIDIA L20 48GB

Official
Ada Lovelace PCIe 2024
FP32
59.8
TFLOPS
VRAM
48 GB
GDDR6
TDP
275 W
217.5 TFLOPS/kW
Bandwidth
864 GB/s
memory
View Providers

Performance Metrics

Peak theoretical throughput by precision type

PrecisionPeak TFLOPSEfficiency
INT8 239.0 0.869 TFLOPS/W
FP8 239.0 0.869 TFLOPS/W
FP16 119.5 0.435 TFLOPS/W
BF16 119.5 0.435 TFLOPS/W
TF32 59.8 0.217 TFLOPS/W
FP32 59.8 0.217 TFLOPS/W
FP8 Efficiency
0.869 TFLOPS/W
239.0 TFLOPS / 275W
FP16 Efficiency
0.435 TFLOPS/W
119.5 TFLOPS / 275W
FP32 Efficiency
0.217 TFLOPS/W
59.8 TFLOPS / 275W

Power Specifications

TDP

275 W

Max Power

316 W

Power Connector

PCIe 8-pin

Cooling

Air

Memory Specifications

Capacity

48 GB

Type

GDDR6

Bandwidth

864 GB/s

Interface

--

Hardware & Design

Form Factor

PCIe

Architecture

Ada Lovelace

Process Node

--

Launch Year

2024

Variant

48GB

Market Segment

Data Center

Common Use Cases

General Compute AI/ML Workloads Data Processing

The NVIDIA L20 is optimized for high-performance computing tasks with Ada Lovelace architecture delivering 59.8 TFLOPS of compute power.

Where to Rent

Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.

Browse GPU Cloud Providers

Similar GPUs

NVIDIA L40S 48GB

PCIe · 2023
FP32: 91.6 TFLOPS
Compare vs L40S

NVIDIA RTX 6000 Ada 48GB

PCIe · 2023
FP32: 91.1 TFLOPS
Compare vs RTX 6000 Ada

NVIDIA L40 48GB

PCIe · 2023
FP32: 90.5 TFLOPS
Compare vs L40

NVIDIA RTX 5000 Ada 32GB

PCIe · 2023
FP32: 65.3 TFLOPS
Compare vs RTX 5000 Ada

Stay Updated on GPU Releases

Get notified when new GPUs are added or specifications are updated.

Loading verification...

No spam, unsubscribe anytime.

Back to GPUs