NVIDIA L4

This is a GPU manufactured with TSMC 5nm process, based on Nvidia Ada Lovelace architecture and released on Mar 2023. It features 35.8 billion transistors, 7424 CUDA cores and 24GB GDDR6 memory, with 48MB L2 cache, theoretical performance of 30.29TFLOPS, with total power consumption of 72W.

Graphics Card

[Report Issues]

Release Date

Mar 2023

Generation

Tesla Ada(Lxx)

Type

Professional

Bus Interface

PCIe 4.0 x16

Clock Speeds

[Report Issues]

Base Clock

795 MHz

Boost Clock

2040 MHz

Memory Clock

1563 MHz

Memory

[Report Issues]

Memory Size

24GB

Memory Type

GDDR6

Memory Bus

192bit

Bandwidth

300.1GB/s

Render Config

[Report Issues]

SM Count

60

Shading Units

7424

TMUs

240

ROPs

80

Tensor Cores

240

RT Cores

60

L1 Cache

128 KB (per SM)

L2 Cache

48 MB

Theoretical Performance

[Report Issues]

Pixel Rate

163.2 GPixel/s

Texture Rate

489.6 GTexel/s

FP16 (half)

30.29 TFLOPS

FP32 (float)

30.29 TFLOPS

FP64 (double)

473.3 GFLOPS

Graphics Processor

[Report Issues]

GPU Name

AD104

GPU Variant

AD104-???-A1

Architecture

Ada Lovelace

Foundry

TSMC

Process Size

5 nm

Transistors

35.8 billion

Die Size

294 mm²

Board Design

[Report Issues]

TDP

72W

Suggested PSU

250 W

Outputs

No outputs

Power Connectors

None

Graphics Features

[Report Issues]

DirectX

12 Ultimate (12_2)

OpenGL

4.6

OpenCL

3.0

Vulkan

1.3

CUDA

8.9

Shader Model

6.8

Rankings

[Report Issues]

FP32 (float)

NVIDIA A10G 12 GB GDDR6

31.52 TFLOPS

NVIDIA A10 PCIe 24 GB GDDR6

31.24 TFLOPS

NVIDIA GeForce RTX 3080 12 GB 12 GB GDDR6X

30.64 TFLOPS

NVIDIA L4 24 GB GDDR6

30.29 TFLOPS

NVIDIA GeForce RTX 3080 10 GB GDDR6X

29.77 TFLOPS

NVIDIA GeForce RTX 4070 12 GB GDDR6X

29.15 TFLOPS

NVIDIA GeForce RTX 4070 AD103 12 GB GDDR6X

29.15 TFLOPS

Related Comparisons

1

NVIDIA Tesla T4 vs NVIDIA L4

2

NVIDIA L4 vs NVIDIA A100 PCIe

3

NVIDIA A10 PCIe vs NVIDIA L4

4

NVIDIA A10G vs NVIDIA L4

5

NVIDIA L40S vs NVIDIA L4

6

NVIDIA GeForce RTX 4090 D vs NVIDIA L4

7

NVIDIA L4 vs NVIDIA Tesla V100 PCIe 32 GB

8

NVIDIA L4 vs NVIDIA A100 PCIe 80 GB

9

NVIDIA L4 vs NVIDIA Tesla C2050

10

NVIDIA L4 vs NVIDIA Quadro P2000 Mobile

Related News

1

Jaguar Shores: Intel's Next-Generation AI Chip to Succeed Falcon Shores

2

NVIDIA Expands Data Center Portfolio with GB200 NVL4 and H200 NVL PCIe GPU

3

NVIDIA Blackwell GPU's First Benchmark Results: Up to 2.2x Performance Boost

4

Shockwaves in the Chip Industry! Reports Claim Apple, Samsung, and Qualcomm Compete to Acquire Intel

5

A 600W Performance Beast is Here! First Real Image of RTX 5090 Unveiled with Massive Size

6

AI Servers Capture One-Third of Global Market: Dell Emerges as Leading Giant

7

NVIDIA DGX B200 Makes Retail Debut: Equipped with 8 B200 GPUs

8

The Landscape of the Three Big Hardware Giants Has Completely Changed! AMD Triumphs Over Intel and Takes on NVIDIA

9

AMD Launches Next-Generation EPYC, Instinct, and PRO Series Products

10

AMD CEO Dr. Lisa Su: Data Center First