NVIDIA A100 PCIe 80 GB vs NVIDIA A16 PCIe

Comparison of NVIDIA A100 PCIe 80 GB with 80 GB HBM2e and 6,912 cores vs NVIDIA A16 PCIe with 16 GB GDDR6 and 1,280 cores.

Loading...

Performance Rating

NVIDIA A100 PCIe 80 GB outperforms NVIDIA A16 PCIe by 550.51% 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 A16 PCIe

3.9

NVIDIA A16 PCIe

3.9

Contents:

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

Memory

Memory Size

🔥 +400% 80 ГБ
16 ГБ ×4 (64 ГБ)

Memory Type

HBM2e GDDR6

Memory Bandwidth

🔥 1.94 TB/s
200.1 GB/s ×4 (800.4 GB/s)

Memory Bus Width

5,120 бит 128 бит ×4 (512 бит)

ML Performance

FP16 (Half Precision)

🔥 +1,635% 77.97 TFLOPS
4.493 TFLOPS

BF16 (Brain Float)

🔥 311.84 TFLOPS
No

TF32 (TensorFloat)

🔥 155.92
No

Compute Power

FP32 (Single Precision)

🔥 +334% 19.49 TFLOPS
4.493 TFLOPS

FP64 (Double Precision)

🔥 +6,842% 9.746 TFLOPS
0.1404 TFLOPS

CUDA Cores

🔥 +440% 6,912
1,280 ×4 (5120)

RT Cores

No
🔥 10 ×4 (40)

Architecture & Compatibility

GPU Architecture

Ampere Ampere

SM (Streaming Multiprocessor)

🔥 +980% 108
10

PCIe Version

PCIe 4.0 x16 PCIe 4.0 x8

ML Software Support

CUDA Version

8.0
🔥 8.6

Clocks & Performance

Base Clock

1,065
🔥 +23% 1,312

Boost Clock

1,410
🔥 +24% 1,755

Memory Clock

1,512
🔥 +3% 1,563

Power Consumption

TDP/TGP

300 W
🔥 -17% 250 W

Recommended PSU

700 W
🔥 -14% 600 W

Power Connector

8-pin EPS 8-pin EPS

Rendering

Texture Units (TMU)

🔥 +980% 432
40 ×4 (160)

ROP

No
🔥 10 ×4 (40)

L2 Cache

🔥 +3,900% 80 MB
2 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

June 28, 2021 April 12, 2021

Display Outputs

No outputs
No outputs

Renting is cheaper than buying