NVIDIA A100 PCIe 80 GB vs ZOTAC RTX 3070 Ti AMP Holo

Comparison of NVIDIA A100 PCIe 80 GB with 80 GB HBM2e and 6,912 cores vs ZOTAC RTX 3070 Ti AMP Holo with 8 GB GDDR6X and 6,144 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

NVIDIA A100 PCIe 80 GB

NVIDIA A100 PCIe 80 GB

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

ZOTAC RTX 3070 Ti AMP Holo

ZOTAC RTX 3070 Ti AMP Holo

Contents:

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

Memory

Memory Size

80 GB 8 GB

Memory Type

HBM2e GDDR6X

Memory Bandwidth

1.94 TB/s 608.3 GB/s

Memory Bus Width

5,120 бит 256 бит

ML Performance

FP16 (Half Precision)

77.97 TFLOPS 22.49 TFLOPS

BF16 (Brain Float)

311.84 TFLOPS No

TF32 (TensorFloat)

155.92 No

Compute Power

FP32 (Single Precision)

19.49 TFLOPS 22.49 TFLOPS

FP64 (Double Precision)

9.746 TFLOPS 0.3514 TFLOPS

CUDA Cores

6,912 6,144

RT Cores

No 48

Architecture & Compatibility

GPU Architecture

Ampere Ampere

SM (Streaming Multiprocessor)

108 48

PCIe Version

PCIe 4.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

8.0
🔥 8.6

Clocks & Performance

Base Clock

1,065 1,575

Boost Clock

1,410 1,830

Memory Clock

1,512 1,188

Power Consumption

TDP/TGP

🔥 -3% 300 W
310 W

Recommended PSU

700 W 700 W

Power Connector

8-pin EPS 2x 8-pin

Rendering

Texture Units (TMU)

432 192

ROP

No 48

L2 Cache

80 MB 4 MB

Additional

Slots

Dual-slot Triple-slot

Release Date

June 28, 2021 May 31, 2021

Display Outputs

No outputs
1x HDMI 2.1
3x DisplayPort 1.4a

Renting is cheaper than buying