NVIDIA A100 PCIe 80 GB vs NVIDIA L20

Comparison of NVIDIA A100 PCIe 80 GB with 80 GB HBM2e and 6,912 cores vs NVIDIA L20 with 48 GB GDDR6 and 11,776 cores.

Loading...

Performance Rating

NVIDIA L20 outperforms NVIDIA A100 PCIe 80 GB by 12.17% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA A100 PCIe 80 GB

25.6

NVIDIA A100 PCIe 80 GB

25.6
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA L20

28.8

NVIDIA L20

28.8

Contents:

Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Additional

Memory

Memory Size

🔥 +67% 80 ГБ
48 ГБ

Memory Type

HBM2e GDDR6

Memory Bandwidth

🔥 1.94 TB/s
864.0 GB/s

Memory Bus Width

5,120 бит 384 бит

ML Performance

FP16 (Half Precision)

🔥 +31% 77.97 TFLOPS
59.35 TFLOPS

BF16 (Brain Float)

🔥 311.84 TFLOPS
No

TF32 (TensorFloat)

🔥 155.92
No

Compute Power

FP32 (Single Precision)

19.49 TFLOPS
🔥 +205% 59.35 TFLOPS

FP64 (Double Precision)

🔥 +951% 9.746 TFLOPS
0.9274 TFLOPS

CUDA Cores

6,912
🔥 +70% 11,776

RT Cores

No
🔥 92

Architecture & Compatibility

GPU Architecture

Ampere Ada Lovelace

SM (Streaming Multiprocessor)

🔥 +17% 108
92

PCIe Version

PCIe 4.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

8.0
🔥 8.9

Clocks & Performance

Base Clock

1,065
🔥 +35% 1,440

Boost Clock

1,410
🔥 +79% 2,520

Memory Clock

1,512
🔥 +49% 2,250

Power Consumption

TDP/TGP

300 W
🔥 -8% 275 W

Recommended PSU

700 W
🔥 -14% 600 W

Power Connector

8-pin EPS 1x 16-pin

Rendering

Texture Units (TMU)

🔥 +17% 432
368

ROP

No
🔥 92

L2 Cache

80 MB
🔥 +20% 96 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

June 28, 2021 Nov. 16, 2023

Display Outputs

No outputs
4x DisplayPort 1.4a

Renting is cheaper than buying