GIGABYTE AORUS RTX 5090 XTREME WATERFORCE vs XFX XFX QICKSILVER MagAir RX 7800 XT

Comparison GIGABYTE AORUS RTX 5090 XTREME WATERFORCE with 32 GB GDDR7 and 21,760 cores vs XFX XFX QICKSILVER MagAir RX 7800 XT with 16 GB GDDR6 and 3,840 cores.

Loading...

Performance Rating

GIGABYTE AORUS RTX 5090 XTREME WATERFORCE outperforms XFX XFX QICKSILVER MagAir RX 7800 XT by 173.29% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

GIGABYTE AORUS RTX 5090 XTREME WATERFORCE

46.5

GIGABYTE AORUS RTX 5090 XTREME WATERFORCE

46.5
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

XFX XFX QICKSILVER MagAir RX 7800 XT

17.0

XFX XFX QICKSILVER MagAir RX 7800 XT

17.0

The GIGABYTE AORUS RTX 5090 XTREME WATERFORCE dramatically outperforms the XFX XFX QICKSILVER MagAir RX 7800 XT, leading by 173% in the overall GPI performance index. For machine learning, the GIGABYTE AORUS RTX 5090 XTREME WATERFORCE has the edge in VRAM (32 vs 16 GB) and FP16 performance (+55%). For gaming, the GIGABYTE AORUS RTX 5090 XTREME WATERFORCE delivers 209% more FP32 throughput, and the GIGABYTE AORUS RTX 5090 XTREME WATERFORCE has 183% more RT cores. In performance per watt, the GIGABYTE AORUS RTX 5090 XTREME WATERFORCE is 42% more efficient at 575W TDP vs 263W for the XFX XFX QICKSILVER MagAir RX 7800 XT.

Contents:

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

Memory

Memory Size

🔥 +100% 32 ГБ
16 ГБ

Memory Type

GDDR7 GDDR6

Memory Bandwidth

🔥 1.79 TB/s
624.1 GB/s

Memory Bus Width

512 бит 256 бит

ML Performance

FP16 (Half Precision)

🔥 +55% 115.5 TFLOPS
74.65 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +209% 115.5 TFLOPS
37.32 TFLOPS

FP64 (Double Precision)

1.805 TFLOPS
🔥 +64,598,238% 1,166,000.0 TFLOPS

CUDA Cores

🔥 +467% 21,760
3,840

RT Cores

🔥 +183% 170
60

Architecture & Compatibility

GPU Architecture

Blackwell 2.0 RDNA 3.0

SM (Streaming Multiprocessor)

🔥 170
No

PCIe Version

PCIe 5.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

12.0 No

CUDA Toolkit (first supported)

v12

CUDA Toolkit status

Supported Supported

Clocks & Performance

Base Clock

🔥 +56% 2,017
1,295

Boost Clock

🔥 +9% 2,655
2,430

Memory Clock

1,750
🔥 +39% 2,438

Power Consumption

Recommended PSU

950 W
🔥 -37% 600 W

Power Connector

1x 16-pin 2x 8-pin

TDP/TGP

575 W
🔥 -54% 263 W

Rendering

Texture Units (TMU)

🔥 +183% 680
240

ROP

🔥 +183% 170
60

L2 Cache

🔥 +2,300% 96 MB
4 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

Jan. 30, 2025 June 18, 2024

Display Outputs

1x HDMI 2.1b
3x DisplayPort 2.1b
1x HDMI 2.1a
3x DisplayPort 2.1

Renting is cheaper than buying