NVIDIA A100 PCIe 80 GB vs NVIDIA GeForce RTX 4070 10 GB

Comparison of NVIDIA A100 PCIe 80 GB with 80 GB HBM2e and 6,912 cores vs NVIDIA GeForce RTX 4070 10 GB with 10 GB GDDR6X and 7,168 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

NVIDIA GeForce RTX 4070 10 GB

13.7

NVIDIA GeForce RTX 4070 10 GB

13.7

Contents:

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

Memory

Memory Size

80 GB 10 ГБ

Memory Type

HBM2e GDDR6X

Memory Bandwidth

1.94 TB/s 420.2 GB/s

Memory Bus Width

5,120 бит 160 бит

ML Performance

FP16 (Half Precision)

77.97 TFLOPS 36.13 TFLOPS

BF16 (Brain Float)

311.84 TFLOPS No

TF32 (TensorFloat)

155.92 No

Compute Power

FP32 (Single Precision)

19.49 TFLOPS 36.13 TFLOPS

FP64 (Double Precision)

9.746 TFLOPS 0.5645 TFLOPS

CUDA Cores

6,912 7,168

RT Cores

No 56

Architecture & Compatibility

GPU Architecture

Ampere Ada Lovelace

SM (Streaming Multiprocessor)

108 56

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 2,355

Boost Clock

1,410 2,520

Memory Clock

1,512 1,313

Power Consumption

TDP/TGP

300 W
🔥 -27% 220 W

Recommended PSU

700 W
🔥 -21% 550 W

Power Connector

8-pin EPS 1x 16-pin

Rendering

Texture Units (TMU)

432 224

ROP

No 56

L2 Cache

80 MB 48 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

June 28, 2021 No

Display Outputs

No outputs
1x HDMI 2.1
3x DisplayPort 1.4a

Renting is cheaper than buying