NVIDIA GeForce RTX 4090 vs NVIDIA RTX A6000

VS

NVIDIA GeForce RTX 4090 NVIDIA RTX A6000

We compared a Desktop platform GPU: 24GB VRAM GeForce RTX 4090 and a Professional market GPU: 48GB VRAM RTX A6000 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce RTX 4090's Advantages

Released 1 years and 11 months late

Boost Clock has increased by 40% (2520MHz vs 1800MHz)

Larger VRAM bandwidth (1008GB/s vs 768.0GB/s)

5632 additional rendering cores

NVIDIA RTX A6000's Advantages

More VRAM (48GB vs 24GB)

Lower TDP (300W vs 450W)

Score

Benchmark

FP32 (float)

GeForce RTX 4090 +113%

82.58 TFLOPS

RTX A6000

38.71 TFLOPS

3DMark Time Spy

GeForce RTX 4090 +105%

36541

RTX A6000

17796

Blender

GeForce RTX 4090 +132%

12921

RTX A6000

5549

OctaneBench

GeForce RTX 4090 +112%

1278

RTX A6000

602

Shadow of the Tomb Raider 2160p

GeForce RTX 4090 +85%

185

RTX A6000

100

Shadow of the Tomb Raider 1440p

GeForce RTX 4090 +69%

280

RTX A6000

165

Shadow of the Tomb Raider 1080p

GeForce RTX 4090 +35%

304

RTX A6000

225

Battlefield 5 1080p

GeForce RTX 4090 +6%

213

RTX A6000

200

GTA 5 2160p

GeForce RTX 4090 +73%

167

RTX A6000

96

GTA 5 1440p

GeForce RTX 4090 +92%

185

RTX A6000

96

GTA 5 1080p

GeForce RTX 4090 +16%

186

RTX A6000

160

GeForce RTX 4090

VS

RTX A6000

Graphics Card

Sep 2022

Release Date

Oct 2020

GeForce 40

Generation

Quadro Ampere

Desktop

Type

Professional

PCIe 4.0 x16

Bus Interface

PCIe 4.0 x16

Clock Speeds

2235MHz

Base Clock

1410MHz

2520MHz

Boost Clock

1800MHz

1313MHz

Memory Clock

2000MHz

Memory

24GB

Memory Size

48GB

GDDR6X

Memory Type

GDDR6

384bit

Memory Bus

384bit

1008 GB/s

Bandwidth

768.0 GB/s

Render Config

128

SM Count

84

-

Compute Units

-

16384

Shading Units

10752

512

TMUs

336

176

ROPs

112

512

Tensor Cores

336

128

RT Cores

84

128 KB (per SM)

L1 Cache

128 KB (per SM)

72MB

L2 Cache

6MB

Theoretical Performance

443.5 GPixel/s

Pixel Rate

201.6 GPixel/s

1290 GTexel/s

Texture Rate

604.8 GTexel/s

82.58 TFLOPS

FP16 (half)

38.71 TFLOPS

82.58 TFLOPS

FP32 (float)

38.71 TFLOPS

1290 GFLOPS

FP64 (double)

604.8 GFLOPS

Graphics Processor

AD102

GPU Name

GA102

AD102-300-A1

GPU Variant

-

Ada Lovelace

Architecture

Ampere

TSMC

Foundry

Samsung

5 nm

Process Size

8 nm

76,300 million

Transistors

28,300 million

609mm²

Die Size

628mm²

Board Design

450W

TDP

300W

850W

Suggested PSU

700W

1x HDMI 2.1 3x DisplayPort 1.4a

Outputs

4x DisplayPort 1.4a

1x 16-pin

Power Connectors

8-pin EPS

Graphics Features

12 Ultimate (12_2)

DirectX

12 Ultimate (12_2)

4.6

OpenGL

4.6

3.0

OpenCL

3.0

1.3

Vulkan

1.3

8.9

CUDA

8.6

6.7

Shader Model

6.7

Related GPU Comparisons

1

NVIDIA GeForce RTX 4090 vs NVIDIA A100 PCIe 80 GB

2

NVIDIA GeForce RTX 4090 vs NVIDIA Tesla V100 PCIe 32 GB

3

NVIDIA GeForce RTX 4090 vs NVIDIA RTX 6000 Ada

4

NVIDIA GeForce RTX 4080 SUPER vs NVIDIA GeForce RTX 4090

5

NVIDIA GeForce RTX 4090 vs NVIDIA H100 SXM5

6

NVIDIA GeForce RTX 4090 vs NVIDIA L40S

7

NVIDIA RTX A6000 vs NVIDIA A100 PCIe 80 GB

8

NVIDIA GeForce RTX 4090 vs AMD Radeon HD 6870 1600SP Edition

9

NVIDIA GeForce RTX 4090 vs AMD Radeon HD 8730 OEM

10

NVIDIA GeForce RTX 4090 vs AMD Radeon R7 350