GIGABYTE AORUS RTX 5090 XTREME WATERFORCE WB vs Intel Data Center GPU Max NEXT

Comparison of GIGABYTE AORUS RTX 5090 XTREME WATERFORCE WB with 32 GB GDDR7 and 21,760 cores vs Intel Data Center GPU Max NEXT with 128 GB HBM2e and 20,480 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

GIGABYTE AORUS RTX 5090 XTREME WATERFORCE WB

GIGABYTE AORUS RTX 5090 XTREME WATERFORCE WB

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

Intel Data Center GPU Max NEXT

62.1

Intel Data Center GPU Max NEXT

62.1

Contents:

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

Memory

Memory Size

32 GB 128 ГБ

Memory Type

GDDR7 HBM2e

Memory Bandwidth

1.79 TB/s
🔥 +79% 3.21 TB/s

Memory Bus Width

512 бит 8,192 бит

ML Performance

FP16 (Half Precision)

115.5 TFLOPS 65.54 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

115.5 TFLOPS 65.54 TFLOPS

FP64 (Double Precision)

1.805 TFLOPS 65.54 TFLOPS

CUDA Cores

21,760 20,480

RT Cores

170 160

Architecture & Compatibility

GPU Architecture

Blackwell 2.0 Generation 12.5

SM (Streaming Multiprocessor)

170 No

PCIe Version

PCIe 5.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

12.0 No

Clocks & Performance

Base Clock

2,017 900

Boost Clock

2,655 1,600

Memory Clock

1,750 1,565

Power Consumption

TDP/TGP

🔥 -28% 575 W
800 W

Recommended PSU

🔥 -21% 950 W
1200 W

Power Connector

1x 16-pin 8-pin EPS

Rendering

Texture Units (TMU)

680 1,280

ROP

170 160

L2 Cache

96 MB 408 MB

Benchmarks

MLPerf, llama2-70b-99.9 (UINT4)

527.5 tokens/s

MLPerf, llama3.1-8b (UINT4)

1 337 tokens/s

MLPerf, llama3.1-8b-edge (UINT4)

1 652 tokens/s

llama.cpp, llama-2-7b-Q4_0

8.21 tokens/s

Additional

Slots

Dual-slot OAM Module

Release Date

Jan. 30, 2025 No

Display Outputs

1x HDMI 2.1b
3x DisplayPort 2.1b
No outputs

Renting is cheaper than buying